© 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. 1-CLT-HP
    7. 9318
    Prev
    Next
    INDEX
    Explanations

    U

    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
     u
    -0.60
     U
    -0.58
    anser
    -0.50
     continued
    -0.48
     let
    -0.47
     der
    -0.46
    うた
    -0.45
     cost
    -0.45
    UNG
    -0.44
     !=
    -0.43
    POSITIVE LOGITS
     NUKAT
    0.70
    clusal
    0.59
     архивлан
    0.59
    BeginContext
    0.57
    sizeCache
    0.56
    出版年
    0.56
     חיצוניים
    0.53
    Hochspringen
    0.53
    μιουργ
    0.53
     Accesat
    0.53
    Activations Density 0.013%

    No Known Activations