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. 1-CLT-HP
    4. 12744
    Prev
    Next
    INDEX
    Explanations

    epi

    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
    Erreferentziak
    -0.54
    BeginInit
    -0.52
    出版年
    -0.52
    :✨
    -0.50
     RoutedEventArgs
    -0.49
    Välislingid
    -0.48
    HandlerContext
    -0.47
     StatelessWidget
    -0.47
     matchs
    -0.47
     lid
    -0.47
    POSITIVE LOGITS
    gjenge
    0.50
    يكب
    0.46
     verden
    0.45
     japonesa
    0.45
     itemprop
    0.45
     calabaza
    0.45
     Shalom
    0.44
    Virtual
    0.43
     patru
    0.43
     Ethio
    0.42
    Activations Density 0.008%

    No Known Activations