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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14021
    Prev
    Next
    INDEX
    Explanations

    the fragment "Fi" as part of a word or brand name, also flagging bracketed letters

    oai_token-act-pair · gemini-2.0-flash

    Code and technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     faſt
    -0.59
    statusBar
    -0.57
    +#+#
    -0.56
     $_"
    -0.55
     raiſ
    -0.54
     Majefty
    -0.54
     purpoſe
    -0.54
     juſ
    -0.53
    تقاوى
    -0.53
    بوابة
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.60
    StoryboardSegue
    0.52
     GenerationType
    0.47
    Hozzáférés
    0.47
    Bibliograf
    0.46
    RTDA
    0.45
    Appendices
    0.44
    CppCodeGen
    0.44
     usuários
    0.44
    TableAdapter
    0.43
    Activations Density 0.374%

    No Known Activations