© 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. 5-CLT-HP
    7. 1149
    Prev
    Next
    INDEX
    Explanations

    over/than

    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
    клопе
    -0.72
    UnusedPrivate
    -0.69
     незавершена
    -0.69
     ویکی‌پدیا
    -0.68
     nahilalakip
    -0.64
     EconPapers
    -0.63
    存于互联网档案馆
    -0.63
    حياته
    -0.63
     possesso
    -0.61
    GEBURTSDATUM
    -0.61
    POSITIVE LOGITS
    #+#
    0.48
     half
    0.44
    HttpHeaders
    0.43
    ymce
    0.41
    반
    0.39
    mybatisplus
    0.39
     once
    0.37
     Funeral
    0.37
    úgó
    0.36
    venido
    0.35
    Activations Density 0.005%

    No Known Activations