© 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. 8805
    Prev
    Next
    INDEX
    Explanations

    Educ

    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
     Zimmerman
    -0.54
    ithi
    -0.47
    мир
    -0.42
    chengladbach
    -0.42
     peace
    -0.42
    vana
    -0.41
     pozn
    -0.40
     Zimmermann
    -0.40
    ccc
    -0.40
    the
    -0.39
    POSITIVE LOGITS
    httphttps
    0.81
    ActionCreators
    0.72
    DoubleQuotes
    0.70
     للمعارف
    0.66
     CreateTagHelper
    0.63
    rinfo
    0.63
     ivelany
    0.61
     rhestr
    0.61
    sertations
    0.60
    AsUp
    0.60
    Activations Density 0.182%

    No Known Activations