© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95765
    Prev
    Next
    INDEX
    Explanations

    stories and myths

    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
     ")
    
    -0.51
     []).
    -0.50
     normaux
    -0.50
    ]='\
    -0.50
    )$}
    -0.49
    }}]{
    -0.48
    );*/
    -0.47
    ")));
    -0.47
    greenrobot
    -0.47
    )))));
    -0.47
    POSITIVE LOGITS
    MLLoader
    0.67
    клопе
    0.65
    يميديا
    0.63
    帖最后由
    0.62
     opérateur
    0.60
     AspNetCore
    0.59
    etcode
    0.59
    UnsafeEnabled
    0.58
    TagMode
    0.57
    etCode
    0.57
    Activations Density 0.064%

    No Known Activations