© 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. 4-CLT-HP
    7. 861
    Prev
    Next
    INDEX
    Explanations

    Impro

    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
    énario
    -0.55
    TabIndex
    -0.47
    naire
    -0.47
    loads
    -0.46
    stoffe
    -0.45
    udsman
    -0.45
    mik
    -0.45
    ing
    -0.45
    antal
    -0.45
    +#+#
    -0.45
    POSITIVE LOGITS
    vised
    0.73
    viser
    0.66
    vise
    0.65
     unknownFields
    0.63
    JspWriter
    0.61
    pri
    0.59
    VISED
    0.57
    errHandler
    0.56
    visation
    0.56
    visa
    0.55
    Activations Density 0.003%

    No Known Activations