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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91640
    Prev
    Next
    INDEX
    Explanations

    articles or analysis

    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
    ness
    -0.68
     Competition
    -0.56
    ing
    -0.52
     clients
    -0.50
    nion
    -0.49
     Doing
    -0.49
     Eres
    -0.49
    intios
    -0.47
     Pas
    -0.45
     Canyon
    -0.45
    POSITIVE LOGITS
     propOrder
    0.92
     оригіналу
    0.77
    IntoConstraints
    0.75
    ResumeLayout
    0.68
    ButterKnife
    0.67
    eee
    0.66
     RoutedEventArgs
    0.66
     مُعرِّف
    0.63
    eeeee
    0.62
    eeee
    0.61
    Activations Density 0.027%

    No Known Activations