© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10480
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Personensuche
    -0.87
    
    -0.70
    脚注の使い方
    -0.67
    KommentareTeilen
    -0.62
     مرئيه
    -0.62
    writeField
    -0.59
    Datuak
    -0.58
    انيف
    -0.56
     lenker
    -0.56
     noDo
    -0.55
    POSITIVE LOGITS
     offering
    0.59
     providing
    0.54
     so
    0.51
     $"{
    0.51
    olucion
    0.50
    holdet
    0.50
    chapper
    0.50
     making
    0.49
     giving
    0.49
    telser
    0.48
    Activations Density 0.016%

    No Known Activations