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. 6003
    Prev
    Next
    INDEX
    Explanations

    words related to educational programs and teaching

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "distance"

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

    adult education

    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
     girasol
    -0.44
     provo
    -0.42
     bezoek
    -0.42
     roda
    -0.42
    Cloudy
    -0.41
     twar
    -0.41
     Tenure
    -0.40
    yaratan
    -0.40
    ensity
    -0.39
     Чем
    -0.39
    POSITIVE LOGITS
     adult
    0.94
     distance
    0.91
     DISTANCE
    0.85
     Distance
    0.85
     Adult
    0.82
    adult
    0.79
    distance
    0.79
     ADULT
    0.79
    Distance
    0.78
    Adult
    0.78
    Activations Density 1.538%

    No Known Activations