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. 11161
    Prev
    Next
    INDEX
    Explanations

    the word "estou"

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating actions or processes

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

    foreign languages

    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
    #+#
    -0.94
    IntoConstraints
    -0.79
     '\\;'
    -0.73
    Personendaten
    -0.73
     uſed
    -0.70
     nahilalakip
    -0.70
    localctx
    -0.70
    resave
    -0.68
    󠁴
    -0.67
    tagHelperRunner
    -0.66
    POSITIVE LOGITS
     suggesting
    0.45
     sum
    0.45
    list
    0.44
     noting
    0.43
     giving
    0.43
     ktore
    0.43
     sending
    0.42
     knowing
    0.42
     dando
    0.42
    かと
    0.42
    Activations Density 0.431%

    No Known Activations