© 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. 95772
    Prev
    Next
    INDEX
    Explanations

    Encapsulation and omega

    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
     Monfieur
    -1.34
     Efq
    -1.31
     Jefus
    -1.27
     ſmall
    -1.24
     myſelf
    -1.23
     Diſ
    -1.19
     Theſe
    -1.19
     itſelf
    -1.15
     feroit
    -1.13
     Reſ
    -1.13
    POSITIVE LOGITS
     “
    0.71
    ,
    0.71
     
    0.69
     the
    0.69
     an
    0.66
     in
    0.63
     a
    0.61
    -
    0.61
     (
    0.60
     all
    0.58
    Activations Density 0.035%

    No Known Activations