© 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. 3452
    Prev
    Next
    INDEX
    Explanations

    interest

    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
     Roskov
    -1.03
    elemField
    -1.00
    VersionUID
    -0.95
    TagMode
    -0.81
    ArrowToggle
    -0.80
    RTEE
    -0.79
    AndEndTag
    -0.78
    tvguidetime
    -0.77
    MLLoader
    -0.75
    IsMutable
    -0.73
    POSITIVE LOGITS
     concedes
    0.44
     marad
    0.42
     HasFactory
    0.42
     blanches
    0.40
     wears
    0.40
    ueger
    0.40
     تعدى
    0.40
     takes
    0.39
     szabad
    0.39
     ettei
    0.39
    Activations Density 0.011%

    No Known Activations