© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 5939
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
     has
    -0.06
    xF
    -0.06
     is
    -0.05
    xt
    -0.05
    .find
    -0.05
    als
    -0.04
    ram
    -0.04
    _
    -0.04
     abs
    -0.03
     it
    -0.03
    POSITIVE LOGITS
    s
    0.11
    timal
    0.07
    losest
    0.07
     optimal
    0.06
     best
    0.06
     closest
    0.05
    hi
    0.05
    la
    0.05
    arest
    0.05
     shortest
    0.05
    Activations Density 52.184%

    No Known Activations