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. 14167
    Prev
    Next
    INDEX
    Explanations

    the first person perspective being used in a narrative

    oai_token-act-pair · gemini-2.0-flash

    encounter

    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
     CreateTagHelper
    -0.77
    tagHelperRunner
    -0.75
    ształ
    -0.65
     kasarigan
    -0.64
     EdgeInsets
    -0.64
    LookAnd
    -0.63
    parsedMessage
    -0.63
    __':
    
    -0.62
    PreExecute
    -0.61
    AllAfrica
    -0.60
    POSITIVE LOGITS
     encounter
    1.24
     Encounter
    1.14
     encounters
    1.08
    encounter
    1.03
     stumble
    1.02
    Encounter
    1.00
     meet
    0.96
     encountered
    0.95
     encountering
    0.93
     stumbled
    0.91
    Activations Density 1.118%

    No Known Activations