Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 374
    Prev
    Next
    INDEX
    Explanations

    suffering

    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
     فريبيس
    -0.56
    перь
    -0.55
    ribune
    -0.53
    vud
    -0.51
     saites
    -0.49
     hinweg
    -0.48
     aDecoder
    -0.46
    withIdentifier
    -0.46
     ویکی‌پدیای
    -0.46
     archivi
    -0.46
    POSITIVE LOGITS
    styleType
    0.66
    astify
    0.57
    
    0.54
     للاسماء
    0.52
     flattery
    0.50
    Espèce
    0.50
     cristianismo
    0.50
    sitivity
    0.49
    stdc
    0.49
     parson
    0.49
    Activations Density 0.025%

    No Known Activations