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. 16204
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures and equipment, especially in emergency situations

    oai_token-act-pair · gemini-2.0-flash

    'during'

    np_token-act-pair-logits · gemini-2.0-flash

    protection equipment

    np_max-act-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
     EconPapers
    -0.75
     protective
    -0.73
    PROLOG
    -0.71
    ModelSerializer
    -0.65
    Protective
    -0.64
     shields
    -0.63
     barrier
    -0.63
     padding
    -0.62
     Protective
    -0.62
     barriers
    -0.60
    POSITIVE LOGITS
    WriteTagHelper
    0.59
    TargetException
    0.51
    Билгалдахарш
    0.51
     vétérina
    0.49
     sèche
    0.48
     fotografico
    0.48
     nemlig
    0.48
    eseorang
    0.47
    masters
    0.47
     الدولى
    0.47
    Activations Density 2.391%

    No Known Activations