© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    references and links related to academic publications and online resources

    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
    <tbody>
    -0.50
    SwingConstants
    -0.48
     single
    -0.42
    loween
    -0.41
    Примечания
    -0.40
    LikeLike
    -0.40
     Bh
    -0.40
     cap
    -0.39
    /…
    -0.39
    šin
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.97
     beginnetje
    0.76
     Viceroy
    0.75
    sizeCache
    0.75
     Sirs
    0.73
     Shakspeare
    0.71
     Assyrian
    0.71
     Cæsar
    0.70
    typeorm
    0.70
     saddles
    0.69
    Activations Density 1.381%

    No Known Activations