© 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. 1-RES-MATRYOSHKA-DC
    7. 332
    Prev
    Next
    INDEX
    Explanations

    references to disease cases, medical queries, and related database or statistical information

    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
    gnition
    -1.31
    æus
    -1.27
    ratulations
    -1.26
    maining
    -1.16
    nicity
    -1.16
     M
    -1.15
    ercises
    -1.14
    asantry
    -1.14
    ouncil
    -1.13
     J
    -1.13
    POSITIVE LOGITS
     itſelf
    1.86
     Diſ
    1.83
     Anſ
    1.77
     Reſ
    1.77
     ſeveral
    1.74
     myſelf
    1.74
     Perſ
    1.73
     Houſe
    1.71
     ſever
    1.70
     purpoſe
    1.67
    Activations Density 14.002%

    No Known Activations