© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    REQUIRES
    -0.57
     Puzzles
    -0.51
    governor
    -0.50
     humain
    -0.49
     governor
    -0.49
    ALUM
    -0.46
     restantes
    -0.46
    gos
    -0.46
     nào
    -0.46
     universe
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.69
     للمعارف
    0.59
    tvguidetime
    0.57
    XmlAccessType
    0.56
     ſeveral
    0.56
     BoxFit
    0.55
    balleur
    0.54
    ValueStyle
    0.54
     perfons
    0.50
     feveral
    0.50
    Activations Density 0.006%

    No Known Activations