© 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. 95448
    Prev
    Next
    INDEX
    Explanations

    current, array

    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
    setList
    -0.50
    Lily
    -0.50
     Lily
    -0.48
    >"+
    -0.46
    illige
    -0.44
    %>
    -0.44
     Liberty
    -0.43
    hers
    -0.43
    >());
    -0.43
    libft
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.83
     Мексичка
    0.75
     kaarangay
    0.72
     الحره
    0.71
    Попис
    0.70
    <bos>
    0.70
    Билгалдахарш
    0.69
     forceps
    0.68
    Personendaten
    0.65
     pyrite
    0.65
    Activations Density 0.193%

    No Known Activations