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. 74187
    Prev
    Next
    INDEX
    Explanations

    technical language and locations

    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
    ThemeOverlay
    -0.69
    UserScript
    -0.57
     NSError
    -0.57
    }\]
    -0.56
    PMailer
    -0.56
    .";
    
    -0.56
    hatsu
    -0.56
    glicher
    -0.54
     WebView
    -0.54
     inode
    -0.54
    POSITIVE LOGITS
     in
    0.62
     under
    0.58
    ContentAlignment
    0.52
     munka
    0.50
     E
    0.50
    zwald
    0.50
     drop
    0.50
    Erstellt
    0.48
     at
    0.48
     Under
    0.47
    Activations Density 0.000%

    No Known Activations