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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1683
    Prev
    Next
    INDEX
    Explanations

    mentions of real estate and local communities, specifically gated communities

    oai_token-act-pair · gemini-2.0-flash

    Extracted data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     great
    -0.78
     ligiloj
    -0.76
     estimés
    -0.73
     beautiful
    -0.69
     built
    -0.66
     kaarangay
    -0.65
    ьаж
    -0.64
     LoggerFactory
    -0.63
    IsContent
    -0.61
     talented
    -0.60
    POSITIVE LOGITS
     onAnimation
    0.53
    stateMutability
    0.52
     citer
    0.50
    toBe
    0.48
    tintColor
    0.46
    WithString
    0.46
    RectangleBorder
    0.45
    #+#
    0.44
    Sein
    0.44
    ReusableCell
    0.44
    Activations Density 0.839%

    No Known Activations