© 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. 4337
    Prev
    Next
    INDEX
    Explanations

    words related to medical or clinical conditions involving inflammation or disease

    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
    ########.
    -0.63
    انجليز
    -0.60
     فريبيس
    -0.56
    ciclopedia
    -0.50
    menuStrip
    -0.50
     intptr
    -0.50
    jestel
    -0.47
    tanleria
    -0.47
     Eul
    -0.46
     capita
    -0.46
    POSITIVE LOGITS
    ative
    3.67
    ATIVE
    2.66
    atives
    2.14
    atively
    2.11
    ativ
    1.77
    ativo
    1.63
    ativa
    1.62
    ATIVES
    1.59
    ATIV
    1.56
    ativen
    1.55
    Activations Density 0.050%

    No Known Activations