© 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

    method definition for class (negative activations)

    python-code · gemini-2.5-flash-lite

    def keyword

    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
     process
    -0.06
    U
    -0.06
    ram
    -0.05
    um
    -0.05
    u
    -0.05
    us
    -0.03
    ven
    -0.03
    mple
    -0.03
    ure
    -0.03
    's
    -0.03
    Positive Logits
    ates
    0.10
    ating
    0.09
    ation
    0.08
    ate
    0.08
    ated
    0.07
    ata
    0.07
    at
    0.07
    atus
    0.07
    ator
    0.07
    able
    0.06
    Activations Density 99.170%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call or definition start (negative activations)

    python-code · gemini-2.5-flash-lite

    list comprehension index `[j]`

    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
    ][
    -0.03
    .append
    -0.03
    [(
    -0.03
    ((
    -0.02
    _edges
    -0.02
     next
    -0.02
    _edge
    -0.01
     e
    -0.01
     f
    -0.01
    '
    0.00
    Positive Logits
    _grid
    0.03
    structions
    0.02
     grid
    0.02
    adj
    0.01
    .split
    0.01
    grid
    0.01
    A
    0.01
     not
    0.01
    (node
    0.01
     is
    0.01
    Activations Density 51.212%

    No Known Activations