© 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. 5-CLT-HP
    7. 91935
    Prev
    Next
    INDEX
    Explanations

    better

    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
     than
    -0.57
     lèvres
    -0.52
    tring
    -0.49
     sobie
    -0.47
     ביותר
    -0.47
     yeux
    -0.46
     Than
    -0.45
    TableField
    -0.45
     at
    -0.45
    le
    -0.45
    POSITIVE LOGITS
     faster
    0.82
     quicker
    0.81
    GraphicsUnit
    0.74
    ⓧ
    0.71
     schneller
    0.71
     schnell
    0.69
     BoxDecoration
    0.69
    tinyos
    0.66
     slower
    0.63
    faster
    0.63
    Activations Density 0.001%

    No Known Activations