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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16266
    Prev
    Next
    INDEX
    Explanations

    java or C++ code closing blocks with curly braces using varying indentation styles

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     CreateTagHelper
    -0.64
     isang
    -0.48
    epy
    -0.46
     gynhyrchwyd
    -0.44
    ėmis
    -0.44
     Pingback
    -0.43
    Kommun
    -0.43
     myſelf
    -0.42
    <!--[
    -0.42
    Communications
    -0.42
    POSITIVE LOGITS
    
    0.65
     Drapeau
    0.59
    UnusedPrivate
    0.58
    ajoz
    0.57
    ModelList
    0.54
     CiNii
    0.52
     gawas
    0.52
    
    0.52
    titleMargin
    0.52
    :✨
    0.51
    Activations Density 0.488%

    No Known Activations