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. 22-CLT-HP
    4. 74511
    Prev
    Next
    INDEX
    Explanations

    code-related text

    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
     inhale
    -0.47
     aer
    -0.45
     breathing
    -0.45
    cloudf
    -0.44
     breathe
    -0.43
    нительно
    -0.41
     breath
    -0.39
    u
    -0.39
    Bast
    -0.39
    ANGO
    -0.39
    POSITIVE LOGITS
    Composição
    0.75
     للاسماء
    0.69
    AutoScaleMode
    0.68
    Portály
    0.66
    IntoConstraints
    0.63
    colorPrimary
    0.62
    تقاوى
    0.62
     mouseY
    0.61
    UseVisualStyle
    0.61
    shore
    0.61
    Activations Density 0.008%

    No Known Activations