© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2157
    Prev
    Next
    INDEX
    Explanations

    code/markup

    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
     CreateTagHelper
    -0.65
    endphp
    -0.56
    tvguidetime
    -0.52
     vuitton
    -0.50
     exécu
    -0.50
    AppRoutingModule
    -0.48
     चीज़ों
    -0.48
    StoryboardSegue
    -0.48
     UIFont
    -0.48
     propOrder
    -0.48
    POSITIVE LOGITS
     Royal
    0.58
    حياته
    0.56
    Šaltiniai
    0.53
    Royal
    0.52
     Osp
    0.52
     Stability
    0.50
     royale
    0.49
     Mean
    0.49
     Civil
    0.48
    PreferredItem
    0.48
    Activations Density 0.004%

    No Known Activations