Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5961
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations including the word "American"

    oai_token-act-pair · gemini-2.0-flash

    the term "American"

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

    American

    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
    Rè
    -0.47
     Kalman
    -0.45
    CustomAttributes
    -0.44
     plancher
    -0.43
     scolaires
    -0.43
    webElementXpaths
    -0.42
     Söz
    -0.40
     computation
    -0.40
    kitab
    -0.40
     daggers
    -0.39
    POSITIVE LOGITS
    AndEndTag
    1.06
    ConstraintMaker
    0.80
     estekak
    0.77
    +#+
    0.77
    BASEPATH
    0.66
     ISTAT
    0.65
     consultato
    0.65
     SqlConnection
    0.63
    Sucesor
    0.63
    ItemBackground
    0.63
    Activations Density 0.439%

    No Known Activations