© 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. 1-CLT-HP
    7. 15291
    Prev
    Next
    INDEX
    Explanations

    symbol

    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
     symbols
    -0.97
     symbol
    -0.89
     symboles
    -0.79
    symbols
    -0.78
    symbol
    -0.77
     simbol
    -0.76
    rungsseite
    -0.74
     symbole
    -0.73
     Symbols
    -0.71
     símbolos
    -0.70
    POSITIVE LOGITS
    انيف
    0.76
    ativement
    0.50
     kéo
    0.49
    ceum
    0.48
    \{\\
    0.48
    렇
    0.48
    ousine
    0.48
    batim
    0.47
    uário
    0.47
    graphy
    0.46
    Activations Density 0.078%

    No Known Activations