© 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. 42882
    Prev
    Next
    INDEX
    Explanations

    kle

    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
    kle
    -0.82
    HasAnnotation
    -0.74
    новништво
    -0.69
     يتيمه
    -0.68
     random
    -0.67
     iprot
    -0.62
    colorPrimary
    -0.60
    AndEndTag
    -0.58
    msgSender
    -0.57
    pushFollow
    -0.57
    POSITIVE LOGITS
    atically
    0.52
    tly
    0.48
    MLLoader
    0.44
    wic
    0.44
    jaciół
    0.42
    i
    0.41
    uza
    0.39
    opath
    0.38
     oxidizing
    0.38
    CoV
    0.38
    Activations Density 0.029%

    No Known Activations