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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5270
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponentiation to the power of 2

    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
    len
    -0.06
     while
    -0.06
     len
    -0.06
    (len
    -0.05
    idth
    -0.05
    _len
    -0.04
     size
    -0.04
    size
    -0.04
     iter
    -0.04
    _length
    -0.03
    POSITIVE LOGITS
    2
    0.06
    vai
    0.05
    0.04
    _to
    0.04
     +
    0.03
    +
    0.03
     /
    0.03
     +=
    0.03
    .random
    0.03
    bab
    0.03
    Activations Density 48.974%

    No Known Activations