© 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. 5-CLT-HP
    7. 4036
    Prev
    Next
    INDEX
    Explanations

    electrical engineering

    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
    <bos>
    -0.51
     Архів
    -0.50
    kul
    -0.48
     للمعارف
    -0.47
    etheless
    -0.47
    таратура
    -0.46
     مشارکت‌کنندگان
    -0.46
    sher
    -0.46
    meaux
    -0.44
     anivers
    -0.44
    POSITIVE LOGITS
     jScrollPane
    0.63
    InputBorder
    0.61
     actuels
    0.57
     positifs
    0.55
     jambes
    0.54
     vägen
    0.54
     tänka
    0.53
    jsonwebtoken
    0.52
     negativos
    0.52
    current
    0.51
    Activations Density 0.013%

    No Known Activations