© 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. 4-CLT-HP
    7. 2447
    Prev
    Next
    INDEX
    Explanations

    data, specs, numbers

    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
    ResponseWriter
    -0.42
     My
    -0.42
     K
    -0.42
    pruch
    -0.41
     klin
    -0.41
    gridx
    -0.41
     Ah
    -0.41
     ama
    -0.40
    xas
    -0.40
     كندا
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.70
    __":
    0.68
    setVerticalGroup
    0.66
    tadır
    0.64
    曖昧さ回避
    0.62
    ///</
    0.60
     postIndex
    0.60
    脚注の使い方
    0.57
    tvguidetime
    0.57
    ISupport
    0.56
    Activations Density 0.002%

    No Known Activations