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. 6024
    Prev
    Next
    INDEX
    Explanations

    subjective emotional reactions

    oai_token-act-pair · gemini-2.0-flash

    expressions of emotion or sentiment

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

    to

    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
     ويكيميديا
    -0.78
     disambiguazione
    -0.71
    +#+#
    -0.70
    bless
    -0.66
    ItemBackground
    -0.65
     blessings
    -0.59
     betweenstory
    -0.59
     obedience
    -0.58
    ftance
    -0.58
     Vinh
    -0.58
    POSITIVE LOGITS
     be
    0.71
     see
    0.58
     from
    0.55
     us
    0.53
     many
    0.53
     of
    0.52
     know
    0.51
    webElementXpaths
    0.51
     even
    0.50
     say
    0.49
    Activations Density 2.434%

    No Known Activations