© 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. 7172
    Prev
    Next
    INDEX
    Explanations

    mentions of illness or sickness

    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
    abestanden
    -0.62
     Drapeau
    -0.50
    unding
    -0.50
     vain
    -0.50
    佻
    -0.49
     Trit
    -0.48
    wasan
    -0.48
     freg
    -0.47
    quotation
    -0.47
    deen
    -0.47
    POSITIVE LOGITS
     sick
    2.92
    sick
    2.63
    Sick
    2.47
     Sick
    2.44
     SICK
    2.41
     sickness
    2.39
     illness
    2.22
     Sickness
    2.17
     Illness
    2.11
     illnesses
    1.76
    Activations Density 0.009%

    No Known Activations