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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14178
    Prev
    Next
    INDEX
    Explanations

    Chinese words for weather and parts of speech/dictionaries

    oai_token-act-pair · gemini-2.0-flash

    Chinese characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    FieldBuilder
    -0.66
     informée
    -0.63
    ГЛА
    -0.61
    ercises
    -0.56
    memoized
    -0.55
    riculum
    -0.55
    нном
    -0.54
    jectures
    -0.53
    endwhile
    -0.52
     sumpay
    -0.52
    POSITIVE LOGITS
     nakalista
    0.64
    <bos>
    0.64
     <<<<<<<<<<<<<<
    0.63
    ⓧ
    0.61
    例句
    0.55
    رشف
    0.55
    /**
    0.54
    prefixer
    0.49
    GraphicsUnit
    0.49
    Geplaatst
    0.49
    Activations Density 1.292%

    No Known Activations