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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16194
    Prev
    Next
    INDEX
    Explanations

    Tracking and logs

    np_max-act-logits · gemini-2.0-flash

    words and phrases related to managing user access and tracking resource usage in computer systems and applications

    oai_token-act-pair · gemini-2.0-flash

    tracking

    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
     typelib
    -0.69
    styleType
    -0.67
     CreateTagHelper
    -0.67
     getItemId
    -0.62
     &___
    -0.57
    DotNetBar
    -0.54
     onPostExecute
    -0.54
     AppComponent
    -0.53
     FileWriter
    -0.52
    parsedMessage
    -0.52
    POSITIVE LOGITS
    colgroup
    0.53
     సౌకర్య
    0.52
    ьаж
    0.50
    
    0.48
    ことです
    0.47
    zyms
    0.47
     dispozici
    0.46
    ency
    0.46
     Vedi
    0.45
    resizingMask
    0.45
    Activations Density 4.294%

    No Known Activations