© 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. 4-CLT-HP
    7. 283
    Prev
    Next
    INDEX
    Explanations

    urd

    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
    oredCriteria
    -0.61
     domestiques
    -0.53
     silencioso
    -0.52
     domésticos
    -0.51
     gants
    -0.50
    Cyfarwyddwr
    -0.50
     íntimo
    -0.49
     magnético
    -0.49
     eriş
    -0.48
     Atherton
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.62
    wapV
    0.55
    bruch
    0.55
     مشين
    0.54
    BufferedImage
    0.54
    __*/
    0.53
    habi
    0.51
     repr
    0.51
    MenuInflater
    0.50
    wara
    0.50
    Activations Density 0.001%

    No Known Activations