© 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. 1154
    Prev
    Next
    INDEX
    Explanations

    vulnerabilities

    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
     tri
    -0.79
     trim
    -0.79
     Trim
    -0.75
     identity
    -0.65
    trim
    -0.65
     trail
    -0.60
    safety
    -0.60
     Tri
    -0.58
    trimmed
    -0.56
    Trim
    -0.56
    POSITIVE LOGITS
     Jefus
    0.67
    ValueStyle
    0.66
    MigrationBuilder
    0.63
    EDEFAULT
    0.62
    aarrggbb
    0.61
    ſelf
    0.61
     cults
    0.61
     nahilalakip
    0.60
     Communism
    0.60
     itſelf
    0.60
    Activations Density 0.065%

    No Known Activations