© 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. 43998
    Prev
    Next
    INDEX
    Explanations

    documents

    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
    erobic
    -1.03
    e
    -0.72
    Citation
    -0.66
     strained
    -0.64
     NDEBUG
    -0.63
    躇
    -0.59
    euse
    -0.59
    tling
    -0.56
    resh
    -0.55
    eto
    -0.54
    POSITIVE LOGITS
    TagMode
    0.66
    fortawesome
    0.66
    tagHelperRunner
    0.65
    SourceChecksum
    0.62
    styleType
    0.61
    évaluateur
    0.60
    Obrázky
    0.59
     ModelExpression
    0.57
    CloseOperation
    0.55
     Chwiliwch
    0.54
    Activations Density 1.965%

    No Known Activations