© 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

    `.add` attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    .get method, class attributes, or numerical condition

    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
    current
    -0.04
    over
    -0.03
    vious
    -0.03
    in
    -0.02
    ree
    -0.02
    xF
    -0.02
    si
    -0.02
    R
    -0.02
    E
    -0.02
    O
    -0.02
    Positive Logits
    ost
    0.04
    Ä
    0.03
    text
    0.02
    _of
    0.02
     o
    0.01
     j
    0.01
    ol
    0.01
     e
    0.01
    _to
    0.01
     se
    0.01
    Activations Density 39.512%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable in for loop (negative activations)

    python-code · gemini-2.5-flash-lite

    self attribute assignment

    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
    apping
    -0.04
    .position
    -0.04
    ([
    -0.04
     defaultdict
    -0.03
    .e
    -0.03
     {}↵
    -0.03
    ctionary
    -0.03
    .c
    -0.03
     dict
    -0.03
    -0.02
    Positive Logits
    .split
    0.07
    .strip
    0.03
    [str
    0.03
    _string
    0.02
     ""
    0.02
    ="
    0.02
     ('
    0.02
    verage
    0.02
     ("
    0.02
    "{
    0.02
    Activations Density 27.605%

    No Known Activations