© 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. 6355
    Prev
    Next
    INDEX
    Explanations

    references to specific proteins

    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
     للاسماء
    -0.97
    DockStyle
    -0.90
    extAlignment
    -0.84
    CloseOperation
    -0.78
    FieldNumber
    -0.77
     cref
    -0.76
    tagext
    -0.74
     Biv
    -0.72
     createState
    -0.71
    parsedMessage
    -0.68
    POSITIVE LOGITS
     prote
    2.52
     Prote
    2.03
    Prote
    1.90
    prote
    1.37
     protease
    1.32
     PROTE
    1.10
     proté
    0.77
    ]")]
    0.71
     protege
    0.66
    dafrika
    0.58
    Activations Density 0.003%

    No Known Activations