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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1750
    Prev
    Next
    INDEX
    Explanations

    job postings for nurses in the UK's National Health Service

    oai_token-act-pair · gemini-2.0-flash

    hospitals and NHS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    AddTagHelper
    -0.69
    VIAF
    -0.64
    Gweler
    -0.63
    CodedInputStream
    -0.63
    WriteTagHelper
    -0.60
    SuppressMessage
    -0.58
    piram
    -0.57
     Eskimo
    -0.57
     мәкал
    -0.54
    LLocation
    -0.54
    POSITIVE LOGITS
    XmlAccessType
    0.57
    CloseOperation
    0.53
    aarrggbb
    0.50
    +:+
    0.49
    MessageTagHelper
    0.47
     pageContext
    0.45
     gjø
    0.45
     Meade
    0.44
    omycin
    0.44
     patria
    0.44
    Activations Density 8.582%

    No Known Activations