© 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. 40023
    Prev
    Next
    INDEX
    Explanations

    wonder

    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
     suffered
    -0.98
     wonder
    -0.80
    AndEndTag
    -0.73
    featureID
    -0.72
     nahilalakip
    -0.71
    tive
    -0.70
    lived
    -0.70
     mergeFrom
    -0.69
    LookAnd
    -0.67
    ########.
    -0.66
    POSITIVE LOGITS
    Ведь
    0.55
     critical
    0.54
    igans
    0.54
    glers
    0.50
    Transkript
    0.50
    ̚
    0.50
    ddle
    0.48
    :✨
    0.48
    ütfen
    0.48
    getMessage
    0.48
    Activations Density 0.124%

    No Known Activations