© 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. 95422
    Prev
    Next
    INDEX
    Explanations

    creating/building

    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
    Not in Any Lists

    No Comments

    Negative Logits
    form
    -0.65
    out
    -0.62
     form
    -0.55
    no
    -0.47
    ագրություններ
    -0.47
    ful
    -0.46
    I
    -0.44
    oute
    -0.44
    open
    -0.44
    on
    -0.44
    POSITIVE LOGITS
    WithIOException
    0.83
     الحره
    0.79
    aarrggbb
    0.75
     kaarangay
    0.73
    fjspx
    0.73
    yntaxException
    0.73
    '));
    
    0.73
    ")));
    
    0.73
    ″]
    0.70
    '];
    
    0.69
    Activations Density 0.075%

    No Known Activations