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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16338
    Prev
    Next
    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash

    phrases about what a business offers its customers.

    oai_token-act-pair · gemini-2.0-flash

    our/us and nearby words

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     تضيفلها
    -0.68
    Diweddarwch
    -0.49
    ValueStyle
    -0.46
     OFDb
    -0.45
     ivelany
    -0.44
    pēc
    -0.42
    mobileqq
    -0.42
     Hiram
    -0.41
    ClInclude
    -0.41
    enumi
    -0.41
    POSITIVE LOGITS
    }\]
    0.78
    %");
    0.74
    "):
    
    0.71
     }}}{
    0.70
    };*/
    0.70
    ")){
    
    0.69
    ſelves
    0.69
    "){
    
    0.69
     препратки
    0.69
    '):
    
    0.68
    Activations Density 1.329%

    No Known Activations