© 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. 76895
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    AccessorTable
    -0.62
     للمعارف
    -0.59
    ViewImports
    -0.56
    ROIT
    -0.48
    OGND
    -0.46
    MLLoader
    -0.46
    ituary
    -0.45
    retario
    -0.45
    utnik
    -0.45
     vieles
    -0.45
    POSITIVE LOGITS
     two
    2.00
    two
    1.63
     four
    1.63
     three
    1.49
     deux
    1.48
     six
    1.38
     TWO
    1.37
     Two
    1.34
     one
    1.33
     five
    1.33
    Activations Density 0.001%

    No Known Activations