© 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. 45239
    Prev
    Next
    INDEX
    Explanations

    tus

    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
     تضيفلها
    -0.60
     ala
    -0.59
    migrationBuilder
    -0.59
     kasarigan
    -0.54
     Numerade
    -0.53
     SEDS
    -0.53
    iar
    -0.52
    zio
    -0.51
     Wikimedijinoj
    -0.50
    __))
    -0.50
    POSITIVE LOGITS
     fallu
    0.69
    InjectAttribute
    0.65
     tény
    0.60
     odeur
    0.59
    p
    0.59
     identité
    0.57
     szüks
    0.57
    n
    0.56
     déput
    0.56
     felb
    0.56
    Activations Density 0.179%

    No Known Activations