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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11169
    Prev
    Next
    INDEX
    Explanations

    parts of code related to the structure of object-oriented programming

    oai_token-act-pair · gemini-2.0-flash

    curly braces and related syntax in code

    np_token-act-pair-logits · gpt-4o-mini

    parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    principalColumn
    -0.81
     CreateTagHelper
    -0.79
    ValueStyle
    -0.74
    CloseOperation
    -0.71
     ويكيپيديا
    -0.67
    
    -0.67
    InvalidProtocol
    -0.64
    COUVER
    -0.64
    PyExc
    -0.64
    aarrggbb
    -0.63
    POSITIVE LOGITS
     {
    0.67
     {{
    0.58
     after
    0.47
     Antal
    0.46
    κε
    0.44
     fous
    0.43
    {{
    0.43
     {%
    0.42
    ims
    0.42
     Seb
    0.42
    Activations Density 0.434%

    No Known Activations