© 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. 42762
    Prev
    Next
    INDEX
    Explanations

    attended

    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
     attended
    -0.62
     päät
    -0.52
    attended
    -0.48
    yarnpkg
    -0.48
    Παραπομπές
    -0.44
    Kaynakça
    -0.44
     valmist
    -0.43
     ویکی‌آمباردا
    -0.42
    libft
    -0.41
     aught
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.80
    AnimationsModule
    0.77
     Infórmanos
    0.77
    ]--;
    0.72
    OutputType
    0.66
     unknownFields
    0.63
     utafitiHapana
    0.63
     BrowserModule
    0.60
    rede
    0.60
    IKAN
    0.58
    Activations Density 1.562%

    No Known Activations