© 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. 8775
    Prev
    Next
    INDEX
    Explanations

    Center

    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
    C
    -0.57
    D
    -0.48
    M
    -0.48
    N
    -0.47
    Con
    -0.47
    FO
    -0.46
    R
    -0.45
    T
    -0.45
    -
    -0.45
    H
    -0.44
    POSITIVE LOGITS
     itſelf
    1.13
     myſelf
    0.97
    ſelf
    0.97
     ―――――
    0.96
     Theſe
    0.95
     pleaſure
    0.94
    ſelves
    0.91
     Jefus
    0.88
     Reſ
    0.88
     Monfieur
    0.87
    Activations Density 0.085%

    No Known Activations