© 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. 10334
    Prev
    Next
    INDEX
    Explanations

    league

    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
     League
    -1.27
     LEAGUE
    -1.13
    League
    -1.07
     league
    -1.05
    league
    -0.98
    MigrationBuilder
    -0.93
     Leagues
    -0.82
     leagues
    -0.73
    RRect
    -0.73
     незавершена
    -0.72
    POSITIVE LOGITS
    QtCore
    0.38
    Tool
    0.38
     brute
    0.37
     to
    0.37
    elsch
    0.36
    ︎
    0.35
    Optional
    0.35
     обре
    0.35
    لوب
    0.35
    jois
    0.35
    Activations Density 0.172%

    No Known Activations