© 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. 40013
    Prev
    Next
    INDEX
    Explanations

    who

    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
    RectangleBorder
    -0.83
    KommentareTeilen
    -0.80
    AnimationsModule
    -0.80
    AutoScaleMode
    -0.80
    脚注の使い方
    -0.78
    exitRule
    -0.75
     SwiftUI
    -0.73
     NSCoder
    -0.71
     Efq
    -0.71
    تقاوى
    -0.69
    POSITIVE LOGITS
    <bos>
    1.08
     run
    0.52
     marked
    0.52
     pass
    0.50
     have
    0.47
     feel
    0.47
     saw
    0.46
     felt
    0.46
    المشاركات
    0.46
     are
    0.45
    Activations Density 0.065%

    No Known Activations