© 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-CLT-HP
    7. 14359
    Prev
    Next
    INDEX
    Explanations

    liver/hepatitis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esModule
    -0.72
    ArgsConstructor
    -0.69
    MessageTagHelper
    -0.63
     Developments
    -0.63
     developments
    -0.60
    CloseOperation
    -0.59
     समीक्षक
    -0.58
     NSCoder
    -0.56
    ScopeManager
    -0.55
    AddTagHelper
    -0.55
    POSITIVE LOGITS
    ồi
    0.55
     дописавши
    0.54
     in
    0.52
    iconque
    0.52
     parar
    0.50
     quæ
    0.50
     tray
    0.49
     Estadística
    0.49
     referenties
    0.47
    tem
    0.47
    Activations Density 0.029%

    No Known Activations