© 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. 20-CLT-HP
    7. 73466
    Prev
    Next
    INDEX
    Explanations

    optimal

    np_max-act-logits · 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
    Conditions
    -0.66
     חיצוניים
    -0.65
    '])){
    -0.63
     مشين
    -0.62
     Audiodateien
    -0.62
     виправивши
    -0.61
     Exacts
    -0.61
     Conditions
    -0.61
    IVEREF
    -0.60
    RenderAtEndOf
    -0.60
    POSITIVE LOGITS
     boundary
    0.52
     off
    0.48
    SEVERE
    0.47
     Brande
    0.46
     Langer
    0.46
     process
    0.45
     on
    0.45
    ServiceClient
    0.43
     operating
    0.43
     makeStyles
    0.43
    Activations Density 0.000%

    No Known Activations