© 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. 1-CLT-HP
    7. 12322
    Prev
    Next
    INDEX
    Explanations

    Charles

    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
    Charles
    -0.59
     Charles
    -0.54
    UTE
    -0.48
    present
    -0.47
     mous
    -0.47
     CHARLES
    -0.47
    utt
    -0.46
    ute
    -0.46
     جميلة
    -0.45
    Present
    -0.44
    POSITIVE LOGITS
    exitRule
    0.79
     صوتيه
    0.68
    ValueStyle
    0.64
    MigrationBuilder
    0.63
    HasAnnotation
    0.62
     للمعارف
    0.61
    GOTREF
    0.60
    #
    0.60
    yarnpkg
    0.60
    ########.
    0.59
    Activations Density 0.073%

    No Known Activations