© 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. 0-CLT-HP
    7. 44031
    Prev
    Next
    INDEX
    Explanations

    Technical/Exploratory Documents

    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
    Negative Logits
     виправивши
    -0.76
     leech
    -0.73
     Kea
    -0.62
     Treasure
    -0.62
    Treasure
    -0.57
     estekak
    -0.56
    mergeFrom
    -0.55
    weiler
    -0.54
    #
    -0.53
     Leech
    -0.52
    POSITIVE LOGITS
    d
    0.69
    s
    0.66
    )_/¯
    0.61
    INSEE
    0.60
    hogs
    0.60
    dx
    0.59
    nst
    0.57
    dong
    0.56
    dg
    0.55
    hog
    0.54
    Activations Density 1.829%

    No Known Activations