© 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. 0-CLT-HP
    7. 38775
    Prev
    Next
    INDEX
    Explanations

    main

    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
     main
    -2.38
    main
    -2.00
    Main
    -1.72
     MAIN
    -1.70
    MAIN
    -1.64
     Main
    -1.62
     principale
    -1.46
     principali
    -1.33
     hoved
    -1.31
     principais
    -1.30
    POSITIVE LOGITS
    kian
    0.46
    DockStyle
    0.46
    XmlAccessType
    0.45
     ever
    0.44
     corn
    0.42
     applied
    0.42
     custody
    0.41
     ๆ
    0.41
     cross
    0.41
    ansa
    0.41
    Activations Density 0.146%

    No Known Activations