© 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. 0-RES-MATRYOSHKA-DC
    7. 12322
    Prev
    Next
    INDEX
    Explanations

    references to medical symptoms, specifically coughing

    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
    lizia
    -0.60
    таратура
    -0.59
     Providence
    -0.57
    forRoot
    -0.57
     plads
    -0.56
    报
    -0.54
     harian
    -0.54
    ष्ण
    -0.54
    vbo
    -0.54
     KZ
    -0.53
    POSITIVE LOGITS
     cough
    3.08
     Cough
    2.56
    cough
    2.56
     coughing
    2.48
    Cough
    2.44
     coughs
    2.31
     coughed
    2.25
    咳嗽
    1.53
    咳
    1.28
     sneeze
    1.16
    Activations Density 0.003%

    No Known Activations