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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73980
    Prev
    Next
    INDEX
    Explanations

    technical/code-related texts

    np_max-act-logits · 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
     only
    -2.14
    only
    -1.65
    Only
    -1.60
     Only
    -1.53
     ONLY
    -1.49
    ONLY
    -1.35
     только
    -1.32
     seulement
    -1.30
     tylko
    -1.17
     jedynie
    -1.16
    POSITIVE LOGITS
     ویکی‌آمباردا
    0.60
    AsUp
    0.57
    ENODEV
    0.56
    łosi
    0.52
    mybatisplus
    0.50
    ThemeOverlay
    0.50
    }
    
    
    0.49
    PhysRevD
    0.49
    Externé
    0.49
    AttributeSet
    0.48
    Activations Density 0.000%

    No Known Activations