© 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. 43214
    Prev
    Next
    INDEX
    Explanations

    CDF

    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
     CDF
    -0.97
     CD
    -0.94
     CDs
    -0.94
     autorytatywna
    -0.93
    ⓧ
    -0.90
    الإنجليزية
    -0.86
    findpost
    -0.84
     betweenstory
    -0.84
    CDs
    -0.81
    Rhestr
    -0.80
    POSITIVE LOGITS
    ge
    0.52
    re
    0.51
    GE
    0.50
    s
    0.50
    W
    0.50
    d
    0.50
    n
    0.49
    V
    0.48
    namespace
    0.46
    SP
    0.45
    Activations Density 0.080%

    No Known Activations