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. 6008
    Prev
    Next
    INDEX
    Explanations

    words related to money and fundraising events

    oai_token-act-pair · gemini-2.0-flash

    event-related terms and bookings

    np_token-act-pair-logits · gpt-4o-mini
    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
    awtextra
    -0.83
    SourceChecksum
    -0.72
    ]")]
    -0.67
     <>",
    -0.66
    didSet
    -0.65
    fjspx
    -0.64
    InputBorder
    -0.63
     snippetHide
    -0.63
    Tembelea
    -0.60
    日閲覧
    -0.60
    POSITIVE LOGITS
     meal
    0.52
     stayed
    0.49
    signup
    0.48
    ionato
    0.47
     exhibited
    0.46
     Reserve
    0.45
    EXHIB
    0.45
     dépos
    0.45
    λί
    0.45
     Helfer
    0.45
    Activations Density 5.608%

    No Known Activations