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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14139
    Prev
    Next
    INDEX
    Explanations

    code syntax related to HTTP headers, especially "Content-Type"

    oai_token-act-pair · gemini-2.0-flash

    HTTP headers

    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
    uns
    -0.42
    TabStop
    -0.41
    わり
    -0.41
    .
    -0.39
     affaires
    -0.39
    PostMapping
    -0.36
    /
    -0.36
     importanza
    -0.35
     uns
    -0.34
     суда
    -0.34
    POSITIVE LOGITS
     esternos
    0.86
     <=",
    0.81
     Efq
    0.77
    EndProject
    0.75
    uxxxx
    0.70
    
    0.70
    AsUp
    0.69
    '},
    
    0.68
    /**
    0.68
    ंदीखरीदारी
    0.67
    Activations Density 1.168%

    No Known Activations