© 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. 96039
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    DockStyle
    -1.11
    mybatisplus
    -0.88
    脚注の使い方
    -0.85
    expandindo
    -0.83
     Efq
    -0.82
    NameInMap
    -0.79
     مشين
    -0.75
     AssemblyCulture
    -0.75
    AndEndTag
    -0.75
    complexContent
    -0.74
    POSITIVE LOGITS
    ,
    0.46
    8
    0.40
    ẵn
    0.37
     menem
    0.37
    6
    0.36
    nières
    0.36
    arrête
    0.35
     min
    0.35
    7
    0.35
     Min
    0.35
    Activations Density 0.009%

    No Known Activations