© 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. 92018
    Prev
    Next
    INDEX
    Explanations

    up

    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
    invokeLater
    -0.63
    labelledby
    -0.63
    ESOME
    -0.57
    .³
    -0.57
    DataAnnotations
    -0.55
    forChild
    -0.55
    AndEndTag
    -0.53
    itology
    -0.53
    atifying
    -0.52
    ."</
    -0.52
    POSITIVE LOGITS
     on
    0.97
    הערות
    0.59
    on
    0.56
    참고
    0.54
     fain
    0.48
     upon
    0.48
    expandindo
    0.48
     vulgares
    0.47
     signals
    0.46
    сту
    0.46
    Activations Density 0.002%

    No Known Activations