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. 5888
    Prev
    Next
    INDEX
    Explanations

    words related to politics and governance

    oai_token-act-pair · gemini-2.0-flash

    specific terms or concepts related to development and governance

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

    Indian local 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
    oredCriteria
    -0.64
    Datuak
    -0.60
    UpInside
    -0.57
    Cubit
    -0.56
     InputDecoration
    -0.55
    DockStyle
    -0.55
    RenderAtEndOf
    -0.51
    sizeCache
    -0.50
    GEBURTSDATUM
    -0.50
     BoxDecoration
    -0.50
    POSITIVE LOGITS
    Demografia
    0.58
     shrimps
    0.56
     catena
    0.56
     magister
    0.56
     بيها
    0.54
    soever
    0.53
    ophysics
    0.52
     nakalista
    0.51
     GALERÍA
    0.51
    ']").
    0.51
    Activations Density 2.558%

    No Known Activations