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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4822
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    strength or length variable assignment

    python-code · gemini-2.5-flash-lite

    range with length (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
    _per
    -0.01
     per
    -0.01
    per
    -0.01
     are
    -0.01
    ="
    -0.00
     in
    -0.00
    verage
    -0.00
    alc
    -0.00
     list
    -0.00
    (p
    -0.00
    POSITIVE LOGITS
     ]↵
    0.08
     }↵
    0.07
     },↵
    0.07
     is
    0.03
    0.02
    ong
    0.02
    é
    0.02
    æ
    0.02
    å
    0.02
    è
    0.02
    Activations Density 100.000%

    No Known Activations