© 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. 5-CLT-HP
    7. 1236
    Prev
    Next
    INDEX
    Explanations

    negation prefix

    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
     onResponse
    -0.58
     unequivocal
    -0.57
     extrinsic
    -0.56
    Linq
    -0.54
     workable
    -0.54
    gonic
    -0.53
    tainable
    -0.53
     avoidable
    -0.52
     donating
    -0.51
     archaic
    -0.51
    POSITIVE LOGITS
     informée
    0.66
    stylers
    0.64
     فريبيس
    0.60
     تضيفلها
    0.55
    بوابة
    0.52
     EClass
    0.51
    
    0.51
    abestanden
    0.50
     برانيه
    0.48
     ويكيپيديا
    0.47
    Activations Density 0.001%

    No Known Activations