© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42198
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
     
    -0.93
     "
    -0.52
     $
    -0.49
     Say
    -0.48
     “
    -0.48
     C
    -0.47
     '
    -0.47
     li
    -0.46
     L
    -0.46
     k
    -0.46
    POSITIVE LOGITS
     Савезне
    0.92
    RenderAtEndOf
    0.89
    ьаж
    0.89
     تضيفلها
    0.80
     चीज़ों
    0.79
     Chwiliwch
    0.78
     concernés
    0.78
    Према
    0.77
    省市镇
    0.74
     colorés
    0.74
    Activations Density 0.106%

    No Known Activations