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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5904
    Prev
    Next
    INDEX
    Explanations

    uses of the word "but" and other words that indicate a change in direction of the text

    oai_token-act-pair · gemini-2.0-flash

    conjunctions and pronouns in context

    np_token-act-pair-logits · gpt-4o-mini

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     but
    -0.97
    but
    -0.81
    But
    -0.71
     But
    -0.69
     pero
    -0.62
    enumii
    -0.61
     createSprite
    -0.61
     maar
    -0.59
     но
    -0.57
    gdx
    -0.56
    POSITIVE LOGITS
     насељу
    0.70
     they
    0.70
     this
    0.68
     these
    0.68
     also
    0.67
     alſo
    0.66
     the
    0.66
     we
    0.65
     voisins
    0.65
     you
    0.64
    Activations Density 2.742%

    No Known Activations