© 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. 4-CLT-HP
    7. 3531
    Prev
    Next
    INDEX
    Explanations

    rio

    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
    StoryboardSegue
    -0.82
    awtextra
    -0.77
    DockStyle
    -0.73
    theless
    -0.72
     defaultstate
    -0.71
    MigrationBuilder
    -0.71
    basicConfig
    -0.70
    CodeAttribute
    -0.69
     تضيفلها
    -0.69
    UnitTesting
    -0.67
    POSITIVE LOGITS
     use
    0.53
    UserContext
    0.44
    മാ
    0.41
    ***************/
    0.40
     publik
    0.38
     uſe
    0.37
     book
    0.36
     worry
    0.36
     umum
    0.36
    MM
    0.36
    Activations Density 0.003%

    No Known Activations