© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 34
    Prev
    Next
    INDEX
    Explanations

    code completion

    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
    -0.59
    はじめに
    -0.53
    <bos>
    -0.47
     Walkover
    -0.47
     ویکی‌پدیای
    -0.46
    PRWEB
    -0.45
    ("")]
    
    -0.43
     China
    -0.43
    cupa
    -0.43
     nh
    -0.42
    POSITIVE LOGITS
    fillType
    0.68
     arrows
    0.63
    ftagPool
    0.61
     bisect
    0.61
     racer
    0.59
     PPD
    0.59
    InjectAttribute
    0.59
     retries
    0.58
     Patro
    0.58
     arrow
    0.58
    Activations Density 0.008%

    No Known Activations