© 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. 8018
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assigning to head attribute

    python-code · gemini-2.5-flash-lite

    closing list bracket `])` (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
     Calculate
    -0.07
    ain
    -0.07
    etween
    -0.06
     abs
    -0.05
    pe
    -0.04
    inal
    -0.04
    ates
    -0.04
    rite
    -0.04
    ta
    -0.04
     math
    -0.04
    POSITIVE LOGITS
     ]↵
    0.15
     }↵
    0.14
     },↵
    0.13
     instruction
    0.07
    _tasks
    0.06
    0.06
    ype
    0.06
     instructions
    0.06
    own
    0.06
     float
    0.06
    Activations Density 100.000%

    No Known Activations