© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 3626
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable `j` in indexing

    python-code · gemini-2.5-flash-lite

    a followed by separator or call (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    lose
    -0.09
    lo
    -0.07
    lines
    -0.04
    .c
    -0.04
    loc
    -0.02
     depth
    -0.02
    mmand
    -0.02
    ind
    -0.02
     sim
    -0.02
     are
    -0.02
    POSITIVE LOGITS
    Ģ
    0.06
    apac
    0.05
    over
    0.04
    _cost
    0.04
     cost
    0.03
    â
    0.03
    apacity
    0.03
    cores
    0.03
    inal
    0.03
    instance
    0.03
    Activations Density 100.000%

    No Known Activations