© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38834
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
    ing
    -0.67
    ed
    -0.49
    quen
    -0.46
     assets
    -0.43
     quenched
    -0.43
    magine
    -0.42
     responsibly
    -0.42
     liability
    -0.40
    liability
    -0.39
     stedet
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    1.16
    CloseOperation
    1.11
     виправивши
    1.09
    verwijspagina
    1.08
    rungsseite
    1.07
    migrationBuilder
    1.03
     Roskov
    1.03
    sizeCache
    1.02
    ConstraintMaker
    1.02
    tvguidetime
    1.01
    Activations Density 0.030%

    No Known Activations