© 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

    range limits (negative activations)

    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
    osition
    -0.03
    os
    -0.03
    :-
    -0.02
     pos
    -0.02
    ource
    -0.02
    .position
    -0.02
    itude
    -0.02
    vious
    -0.02
    ache
    -0.02
    lf
    -0.02
    Positive Logits
    ð
    0.12
    raph
    0.11
    .edges
    0.10
    graph
    0.10
    edges
    0.10
     edges
    0.10
     edge
    0.10
     Graph
    0.10
     graph
    0.09
    _graph
    0.09
    Activations Density 99.161%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `pow` function calls

    python-code · gemini-2.5-flash-lite

    multiply method name (negative activations)

    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
    gs
    -0.10
    pected
    -0.09
    _coordinates
    -0.07
    ordinate
    -0.07
    ood
    -0.06
    ordinates
    -0.06
    g
    -0.06
     base
    -0.05
    gth
    -0.05
    rue
    -0.04
    Positive Logits
    graph
    0.07
     '#
    0.07
    Ĥ
    0.06
     cur
    0.06
     network
    0.06
    ).
    0.06
    der
    0.06
    de
    0.05
     ('
    0.05
     Returns
    0.05
    Activations Density 100.000%

    No Known Activations