© 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. 16042
    Prev
    Next
    INDEX
    Explanations

    to

    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
     be
    -0.70
     make
    -0.59
     conducta
    -0.56
     provide
    -0.56
    ↵↵
    -0.55
     survie
    -0.55
     get
    -0.54
     cremallera
    -0.49
     test
    -0.49
     present
    -0.48
    POSITIVE LOGITS
     ſeveral
    1.17
     greateſt
    1.01
     Jefus
    1.00
     Efq
    0.97
     itſelf
    0.94
     ſmall
    0.92
     $_"
    0.91
     poffible
    0.91
     fevere
    0.91
     ſta
    0.91
    Activations Density 0.071%

    No Known Activations