© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    Articles

    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
    LookAnd
    -0.57
    simpleType
    -0.55
     InputDecoration
    -0.53
    tagHelperRunner
    -0.53
     transfieras
    -0.52
     cherchés
    -0.51
    ⓘ
    -0.51
     Anson
    -0.49
     EconPapers
    -0.49
    tonsoft
    -0.48
    POSITIVE LOGITS
     history
    0.82
    history
    0.74
     CURIAM
    0.69
     History
    0.63
     historie
    0.61
     Historie
    0.60
    History
    0.58
     Family
    0.57
     family
    0.55
     histories
    0.53
    Activations Density 0.003%

    No Known Activations