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. 16207
    Prev
    Next
    INDEX
    Explanations

    time durations and schedules

    oai_token-act-pair · gemini-2.0-flash

    [uninterpretable]

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

    time

    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
     morning
    -1.05
     midnight
    -1.05
     afternoon
    -1.05
    Afternoon
    -0.96
     hourly
    -0.94
     evening
    -0.93
     hour
    -0.93
     daytime
    -0.92
     Afternoon
    -0.91
     Hours
    -0.91
    POSITIVE LOGITS
    mphony
    0.68
     GenerationType
    0.65
    الحياه
    0.57
    LElement
    0.55
    WebControls
    0.55
     Winter
    0.55
    تقاوى
    0.54
    Externé
    0.53
    SPRING
    0.52
     Weihnachten
    0.52
    Activations Density 1.415%

    No Known Activations