© 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. 91272
    Prev
    Next
    INDEX
    Explanations

    women

    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
    contentLoaded
    -0.64
    parsedMessage
    -0.59
    fromnode
    -0.58
     onAnimation
    -0.58
    Distribuzione
    -0.57
     betweenstory
    -0.56
    glises
    -0.52
     '\\;'
    -0.51
    ännande
    -0.51
    andaag
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.72
    +#+#
    0.63
     энциклопедия
    0.57
    Geplaatst
    0.56
     mercancías
    0.55
    ']->
    0.54
    static
    0.50
    Media
    0.50
    rän
    0.49
    uchos
    0.49
    Activations Density 0.001%

    No Known Activations