© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8989
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Himo
    -0.80
    KommentareTeilen
    -0.66
    parsedMessage
    -0.65
     समीक्षक
    -0.64
    enumii
    -0.63
    ंदीखरीदारी
    -0.61
    ensement
    -0.61
    RefNanny
    -0.57
     متعلقه
    -0.57
     Référence
    -0.57
    POSITIVE LOGITS
    ainville
    0.53
    acchar
    0.50
    setVerticalGroup
    0.49
    ográfico
    0.49
     gén
    0.48
    illips
    0.48
    ecycle
    0.47
    值为
    0.47
    LIK
    0.47
    echos
    0.47
    Activations Density 0.065%

    No Known Activations