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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74024
    Prev
    Next
    INDEX
    Explanations

    code, technical language

    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
    DockStyle
    -0.79
     AssemblyProduct
    -0.77
    Tikang
    -0.72
    ByExample
    -0.69
    XmlEnum
    -0.68
    يميديا
    -0.67
    msgid
    -0.60
    InjectAttribute
    -0.60
    ThemeOverlay
    -0.58
     estimés
    -0.57
    POSITIVE LOGITS
    --)
    
    0.48
    ställning
    0.42
    --){
    0.42
     suivants
    0.41
    ("}\
    0.40
     Muito
    0.40
    IVERS
    0.40
    ")"
    0.40
    تفصیلات
    0.40
    ɵɵ
    0.40
    Activations Density 0.000%

    No Known Activations