© 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. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3801
    Prev
    Next
    INDEX
    Explanations

    references to specific numbered items or symbols in a sequence

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Republican
    -0.53
    共和
    -0.52
    cout
    -0.51
     republican
    -0.50
    :+:
    -0.50
     március
    -0.50
     dags
    -0.49
    Republican
    -0.49
    Viitteet
    -0.48
     lay
    -0.47
    POSITIVE LOGITS
     twenties
    0.84
    enumi
    0.80
    RectangleBorder
    0.78
     sixties
    0.77
     seventies
    0.76
     thirties
    0.74
     fifties
    0.72
     geslacht
    0.72
    modelBuilder
    0.71
     eighties
    0.71
    Activations Density 0.010%

    No Known Activations