© 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. 5-CLT-HP
    7. 5600
    Prev
    Next
    INDEX
    Explanations

    in

    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
     )$
    -0.61
    -${
    -0.54
    :"-"`
    -0.47
     helping
    -0.46
    StoreMessageInfo
    -0.46
     intentando
    -0.43
    obox
    -0.43
    ীব
    -0.43
    liquez
    -0.43
    chism
    -0.43
    POSITIVE LOGITS
     виправивши
    0.77
    basicConfig
    0.77
    bootstrapcdn
    0.70
     NSCoder
    0.67
    HandlerContext
    0.64
    OGND
    0.61
     '\\;'
    0.58
    ervlak
    0.57
    writeField
    0.57
    UnusedPrivate
    0.57
    Activations Density 0.001%

    No Known Activations