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. 14185
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to emphasize a point or opinion

    oai_token-act-pair · gemini-2.0-flash

    thing/reason/purpose

    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
     с
    -0.35
    where
    -0.35
     An
    -0.34
    まま
    -0.34
    sz
    -0.33
    An
    -0.32
    vi
    -0.32
     ***!
    -0.32
     tils
    -0.32
    roll
    -0.32
    POSITIVE LOGITS
     thing
    1.13
     goal
    1.02
     itſelf
    1.00
     purpoſe
    0.96
     Jefus
    0.96
     consequence
    0.96
     reaſon
    0.95
     myſelf
    0.93
     reason
    0.92
     objective
    0.91
    Activations Density 1.433%

    No Known Activations