© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43497
    Prev
    Next
    INDEX
    Explanations

    Addressing the reader "You"

    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
    Obrázky
    -0.80
     crescere
    -0.70
     surla
    -0.69
    anskje
    -0.69
     EconPapers
    -0.66
     مواليد
    -0.66
     ComVisible
    -0.64
    ymce
    -0.64
    apimachinery
    -0.61
    énario
    -0.60
    POSITIVE LOGITS
    s
    0.55
    ся
    0.50
    UVWXYZ
    0.50
     E
    0.46
    MENAFN
    0.46
    hemian
    0.44
    ING
    0.44
     Party
    0.43
     Winter
    0.43
    ing
    0.42
    Activations Density 0.062%

    No Known Activations