© 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. 95763
    Prev
    Next
    INDEX
    Explanations

    people

    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
     people
    -0.60
    PerformLayout
    -0.56
     at
    -0.54
     T
    -0.53
    ChromeDriver
    -0.52
     did
    -0.52
    grafi
    -0.51
     has
    -0.49
     .
    -0.48
     can
    -0.48
    POSITIVE LOGITS
    theless
    0.75
    expandindo
    0.72
     AssemblyCulture
    0.71
    Personensuche
    0.69
    Diweddarwch
    0.69
     cdti
    0.66
    OGND
    0.65
    帖最后由
    0.65
     oprot
    0.63
     houſe
    0.62
    Activations Density 0.375%

    No Known Activations