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. 14147
    Prev
    Next
    INDEX
    Explanations

    words related to religion, good and evil, and morality

    oai_token-act-pair · gemini-2.0-flash

    religion

    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
    <bos>
    -0.66
    ${
    -0.56
     ${
    -0.53
    Välislingid
    -0.51
     TextAppearance
    -0.50
     위한
    -0.50
     sicura
    -0.49
    ølge
    -0.48
    msgid
    -0.48
    aronder
    -0.47
    POSITIVE LOGITS
     Perci
    0.64
     chi̍t
    0.62
     CascadeType
    0.60
     Reinhold
    0.59
     OFDb
    0.56
     Machia
    0.56
     levers
    0.55
    mental
    0.54
    enschutzer
    0.54
     maneuvers
    0.54
    Activations Density 0.747%

    No Known Activations