© 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

    fibonacci sequence start `0, 1`

    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
    101
    -0.03
    etween
    -0.03
    (),
    -0.02
    ():↵
    -0.02
    ĭ
    -0.02
     +=
    -0.02
     break
    -0.02
    .keys
    -0.02
     th
    -0.02
    oth
    -0.02
    Positive Logits
     if
    0.05
    gre
    0.05
     (-
    0.04
    light
    0.04
    25
    0.04
     If
    0.03
     [-
    0.03
     -=
    0.02
    :-
    0.02
    [-
    0.02
    Activations Density 91.295%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    conditional statements or loops (negative activations)

    python-code · gemini-2.5-flash-lite

    creation of lists with fixed size

    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
    visited
    -0.05
     visited
    -0.04
    isited
    -0.04
    or
    -0.03
    rontier
    -0.03
     or
    -0.03
    ep
    -0.03
    -
    -0.03
    hor
    -0.02
     dfs
    -0.02
    Positive Logits
    =True
    0.04
    [
    0.03
    tity
    0.02
    .pop
    0.02
     heapq
    0.02
    70
    0.02
    tail
    0.01
     [[
    0.01
     base
    0.01
     ra
    0.01
    Activations Density 100.000%

    No Known Activations