© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment using tuple unpacking (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute names with 'in', 'max', 'total', 'average'

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    join
    -0.04
    .name
    -0.03
    .id
    -0.03
     Create
    -0.03
    oal
    -0.03
    dex
    -0.03
    itial
    -0.03
    stance
    -0.03
    _idx
    -0.03
    stination
    -0.03
    Positive Logits
    .split
    0.04
    split
    0.03
    .read
    0.03
    .strip
    0.03
    strip
    0.02
    .find
    0.02
    xF
    0.02
    (int
    0.02
    valid
    0.02
    sible
    0.01
    Activations Density 80.690%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list method calls (.append, .remove, .pop) (negative activations)

    python-code · gemini-2.5-flash-lite

    collections.defaultdict

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ^
    -0.04
    (N
    -0.04
    (G
    -0.04
    ():↵
    -0.03
    (list
    -0.03
    .heapp
    -0.03
    (str
    -0.03
    ("
    -0.03
    ()
    -0.03
    ('
    -0.03
    Positive Logits
     between
    0.02
    heck
    0.02
    loat
    0.02
    is
    0.02
     check
    0.02
    .is
    0.02
     Check
    0.02
    lable
    0.02
    are
    0.02
     has
    0.02
    Activations Density 98.119%

    No Known Activations