© 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. 20-CLT-HP
    7. 71895
    Prev
    Next
    INDEX
    Explanations

    Code/unusual text

    np_max-act-logits · 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
     whoſe
    -0.82
     للاسماء
    -0.79
    NUMX
    -0.77
     itſelf
    -0.77
    RenderAtEndOf
    -0.77
    BeginContext
    -0.75
    IsContent
    -0.74
     becauſe
    -0.73
     houſe
    -0.73
     Efq
    -0.73
    POSITIVE LOGITS
     to
    0.43
     or
    0.40
    {~
    0.37
     sont
    0.35
     המ
    0.33
    ook
    0.32
     don
    0.31
     persen
    0.31
     Thumbnails
    0.30
     y
    0.30
    Activations Density 0.001%

    No Known Activations