© 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. 4-CLT-HP
    7. 2102
    Prev
    Next
    INDEX
    Explanations

    punctuation and articles

    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
     lccn
    -0.78
    PMailer
    -0.66
    
    -0.64
    Przypisy
    -0.62
    errHandler
    -0.61
     nahilalakip
    -0.59
    Referències
    -0.59
    providedIn
    -0.58
    #
    -0.56
    Географи
    -0.55
    POSITIVE LOGITS
    view
    0.54
     View
    0.49
     view
    0.47
     săn
    0.46
    View
    0.46
     समीक्षक
    0.45
    seiti
    0.45
    úgó
    0.45
    Autoritní
    0.44
     VIEW
    0.43
    Activations Density 0.003%

    No Known Activations