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. 11078
    Prev
    Next
    INDEX
    Explanations

    words relating to the government and legal system of Swaziland, including names of people and organizations

    oai_token-act-pair · gemini-2.0-flash

    prefixes and patterns involving 'ul' and 'mis'

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

    Swaziland/Eswatini news

    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
    principalTable
    -0.82
     صوتيه
    -0.81
     greateſt
    -0.76
    ArgsConstructor
    -0.73
     ſtate
    -0.72
    RUnlock
    -0.72
    HomeAsUpEnabled
    -0.72
    harapkan
    -0.71
    abetes
    -0.71
    الحياه
    -0.70
    POSITIVE LOGITS
    ul
    0.46
    mis
    0.43
     ul
    0.42
    til
    0.41
     ben
    0.40
    ik
    0.39
    cha
    0.39
    il
    0.37
     Wol
    0.37
    ke
    0.37
    Activations Density 0.110%

    No Known Activations