Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2121
    Prev
    Next
    INDEX
    Explanations

    C# method declarations and code blocks with `set` and `return` statements

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.81
    الحياه
    -0.72
    UnsafeEnabled
    -0.69
    AddTagHelper
    -0.68
     CreateTagHelper
    -0.68
    DoubleQuotes
    -0.68
     @"/
    -0.67
    клопе
    -0.67
    InjectAttribute
    -0.63
    BeginContext
    -0.62
    POSITIVE LOGITS
     critical
    0.57
    critical
    0.51
     Critical
    0.46
     CRITICAL
    0.45
    :✨
    0.44
    Critical
    0.44
    Personensuche
    0.40
     cima
    0.40
    protoimpl
    0.39
    inci
    0.38
    Activations Density 0.983%

    No Known Activations