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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13678
    Prev
    Next
    INDEX
    Explanations

    one

    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
     дописавши
    -0.74
    
    -0.68
    ropods
    -0.65
     endwhile
    -0.65
    menopausal
    -0.63
    TagHelpers
    -0.63
    AddHtmlAttribute
    -0.63
     فريبيس
    -0.62
    WriteLiteral
    -0.62
    хьтан
    -0.61
    POSITIVE LOGITS
     that
    0.49
    B
    0.46
     InputDecoration
    0.45
    leyin
    0.42
    ても
    0.42
    таратура
    0.42
    يتي
    0.41
    U
    0.41
     a
    0.41
     otomatig
    0.40
    Activations Density 0.015%

    No Known Activations