© 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. 5-CLT-HP
    7. 6298
    Prev
    Next
    INDEX
    Explanations

    time

    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
    便
    -0.52
    談社
    -0.50
     complic
    -0.47
     непо
    -0.46
    ض
    -0.44
    wapV
    -0.44
     κό
    -0.44
    zd
    -0.43
    неопр
    -0.43
    しゃ
    -0.41
    POSITIVE LOGITS
     postdoctoral
    0.73
     fellowships
    0.73
    WriteTagHelper
    0.71
    :✨
    0.70
     scholarship
    0.70
     research
    0.68
     fellows
    0.68
     lecturer
    0.66
     teaching
    0.66
     undergraduate
    0.66
    Activations Density 0.000%

    No Known Activations