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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16358
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions relating objects or concepts.

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    AndEndTag
    -0.80
    TypedDataSet
    -0.79
     Himo
    -0.70
    RenderAtEndOf
    -0.70
     للاسماء
    -0.69
     فريبيس
    -0.65
    Personensuche
    -0.63
    DoubleQuotes
    -0.63
    UserScript
    -0.63
    InjectAttribute
    -0.59
    POSITIVE LOGITS
     Grau
    0.45
     also
    0.44
     MotionEvent
    0.44
     Superhosts
    0.44
     chi̍t
    0.43
    oce
    0.42
     Val
    0.42
    acle
    0.41
     Il
    0.41
    NUMX
    0.41
    Activations Density 4.398%

    No Known Activations