© 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. 5-CLT-HP
    7. 91966
    Prev
    Next
    INDEX
    Explanations

    eagle

    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
    sidemargin
    -0.86
     мәкал
    -0.59
     jSON
    -0.56
    GEBURTSDATUM
    -0.55
    scrapy
    -0.54
     termites
    -0.51
    aarrggbb
    -0.50
     Reverso
    -0.50
     ErrIntOverflow
    -0.50
    issan
    -0.49
    POSITIVE LOGITS
     مشارکت‌کنندگان
    0.54
     Given
    0.48
     given
    0.48
    pended
    0.48
     laid
    0.47
     Uptake
    0.47
    aree
    0.47
     retained
    0.47
     Who
    0.46
     darse
    0.46
    Activations Density 0.001%

    No Known Activations