© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38904
    Prev
    Next
    INDEX
    Explanations

    denial/refusal

    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
     refused
    -1.18
     refuse
    -1.12
     refusing
    -1.11
     refusal
    -1.06
     refuses
    -1.06
     itself
    -0.82
     refus
    -0.81
     Refuse
    -0.76
     atmosphere
    -0.75
     refusé
    -0.75
    POSITIVE LOGITS
    tagHelperRunner
    1.27
     ModelExpression
    0.93
    featureID
    0.77
     propOrder
    0.73
    LookAnd
    0.72
    tvguidetime
    0.72
     beginnetje
    0.70
    AccessorTable
    0.69
     nonUne
    0.69
    CppMethod
    0.69
    Activations Density 0.206%

    No Known Activations