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. 11038
    Prev
    Next
    INDEX
    Explanations

    the word "you" or forms.

    oai_token-act-pair · gemini-2.0-flash

    second person pronouns and related modal verbs

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

    You

    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
    BeginContext
    -0.78
    twimg
    -0.65
    stdc
    -0.65
     المعيارى
    -0.64
     piú
    -0.59
     morire
    -0.59
    VIAF
    -0.58
     Signalez
    -0.58
     nahilalakip
    -0.57
     quæ
    -0.56
    POSITIVE LOGITS
     could
    0.76
     can
    0.65
     архивлан
    0.59
     should
    0.59
     Could
    0.58
     shouldn
    0.58
     name
    0.57
     then
    0.57
     us
    0.56
    ConstraintMaker
    0.54
    Activations Density 1.189%

    No Known Activations