© 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. 20-CLT-HP
    7. 72813
    Prev
    Next
    INDEX
    Explanations

    diabetes and related medical

    np_max-act-logits · 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
    parsedMessage
    -0.73
    +#+#
    -0.65
    InitVars
    -0.65
    PreferredItem
    -0.63
    TypedDataSet
    -0.63
    MigrationBuilder
    -0.63
    featureID
    -0.62
     Waray
    -0.60
     Taktlose
    -0.60
    Personendaten
    -0.59
    POSITIVE LOGITS
     met
    0.67
     g
    0.54
    uol
    0.53
    big
    0.51
     big
    0.50
     inc
    0.48
    gli
    0.48
     Big
    0.47
     Jan
    0.47
    gart
    0.47
    Activations Density 0.002%

    No Known Activations