© 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. 987
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
    chk
    -1.63
     likeness
    -0.95
     chk
    -0.73
    Chk
    -0.65
    chkin
    -0.63
    CHK
    -0.62
    اته
    -0.57
     freien
    -0.47
     character
    -0.46
    kose
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.82
    ⓧ
    0.78
    ArrowToggle
    0.73
     betweenstory
    0.73
    TagMode
    0.71
    afficheront
    0.71
    AsUp
    0.68
     StatelessWidget
    0.65
     rhestr
    0.63
     кӀ
    0.62
    Activations Density 0.340%

    No Known Activations