© 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. 15461
    Prev
    Next
    INDEX
    Explanations

    medicine/science

    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
     Wilderness
    -0.58
    caud
    -0.54
    TIL
    -0.53
     DIAL
    -0.53
     esercit
    -0.52
     intptr
    -0.51
    lia
    -0.50
    rard
    -0.49
    rolid
    -0.49
    scryfall
    -0.49
    POSITIVE LOGITS
     للمعارف
    0.58
    homonymie
    0.56
    ot
    0.55
    esModule
    0.54
    ortic
    0.52
    NodeType
    0.49
    MigrationBuilder
    0.49
    e
    0.49
    expandindo
    0.48
    ity
    0.48
    Activations Density 0.017%

    No Known Activations