© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12126
    Prev
    Next
    INDEX
    Explanations

    find

    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
    e
    -0.38
    Swiss
    -0.34
    ь
    -0.33
    gridx
    -0.33
    ToTop
    -0.32
    ing
    -0.31
     swiss
    -0.31
    to
    -0.31
     revisor
    -0.31
     find
    -0.30
    POSITIVE LOGITS
     purpoſe
    0.89
    StoryboardSegue
    0.81
     Meksiku
    0.81
    aarrggbb
    0.79
     Efq
    0.79
     myſelf
    0.79
     Perſ
    0.77
    ^(@)
    0.77
     Diſ
    0.77
    InjectAttribute
    0.77
    Activations Density 0.766%

    No Known Activations