© 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. 95122
    Prev
    Next
    INDEX
    Explanations

    discord

    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
    hes
    -0.62
     diver
    -0.57
    ed
    -0.55
    Zep
    -0.54
    e
    -0.53
    wh
    -0.52
    iver
    -0.49
     hes
    -0.47
    Wh
    -0.47
     differential
    -0.47
    POSITIVE LOGITS
     automatiques
    0.76
    aarrggbb
    0.71
     récents
    0.69
    UseVisualStyle
    0.68
     scolaires
    0.67
    Conclusie
    0.66
     dezelve
    0.66
    Geschiedenis
    0.65
    '],
    0.64
    CLUYE
    0.63
    Activations Density 0.249%

    No Known Activations