© 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. 1-CLT-HP
    7. 45686
    Prev
    Next
    INDEX
    Explanations

    star

    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
     star
    -0.98
    stars
    -0.97
    star
    -0.96
     stars
    -0.92
     estrellas
    -0.88
     Stars
    -0.82
    Stars
    -0.82
    Star
    -0.78
     estrella
    -0.78
     स्टार
    -0.77
    POSITIVE LOGITS
     незавершена
    0.57
    ագրություններ
    0.53
    glGen
    0.52
    VersionUID
    0.47
     yellow
    0.47
     الاطلاع
    0.46
    entable
    0.46
    tania
    0.46
     proposed
    0.45
     predicted
    0.44
    Activations Density 0.019%

    No Known Activations