© 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. 4-CLT-HP
    7. 4447
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     дописавши
    -0.79
     мәкал
    -0.65
    Климат
    -0.57
    UnsafeEnabled
    -0.56
    parsedMessage
    -0.56
    flake
    -0.54
    IBAction
    -0.54
     فريبيس
    -0.54
     machine
    -0.53
     SwitchCompat
    -0.52
    POSITIVE LOGITS
    ंदीखरीदारी
    0.60
     behind
    0.59
     fully
    0.53
    akaian
    0.53
    日閲覧
    0.51
     onBind
    0.49
    BASELINE
    0.49
     adequately
    0.49
     Tapatalk
    0.49
     of
    0.47
    Activations Density 0.003%

    No Known Activations