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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91042
    Prev
    Next
    INDEX
    Explanations

    HW

    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
     NSCoder
    -0.66
    Dermott
    -0.59
     Sili
    -0.56
    bufio
    -0.51
    sik
    -0.50
     mostrarán
    -0.49
    comuna
    -0.49
     tartalomajánló
    -0.48
    出版年
    -0.47
     SIL
    -0.47
    POSITIVE LOGITS
     quæ
    0.79
     dieux
    0.75
    Šaltiniai
    0.64
     ejus
    0.63
     brancas
    0.60
     fjer
    0.60
     varandra
    0.60
     scuro
    0.60
     européennes
    0.60
     raiſ
    0.59
    Activations Density 0.068%

    No Known Activations