© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2195
    Prev
    Next
    INDEX
    Explanations

    code

    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
    :✨
    -0.85
    참고
    -0.77
     kasarigan
    -0.68
    Попис
    -0.63
    MetaObject
    -0.62
    UserScript
    -0.61
    CPtr
    -0.59
     onCreateView
    -0.59
    )++;
    -0.58
     reopen
    -0.58
    POSITIVE LOGITS
    Kjelder
    0.51
    -------------</
    0.49
    اخته
    0.47
     sánh
    0.46
    huis
    0.45
     all
    0.42
    vdash
    0.42
     tổng
    0.41
    <>();
    0.41
    äu
    0.40
    Activations Density 0.005%

    No Known Activations