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. 14145
    Prev
    Next
    INDEX
    Explanations

    proper names of people, companies, and places, especially when combined with terms related to audits or legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    auditing firms

    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
     jScrollPane
    -0.65
    はじめに
    -0.58
     ThemeData
    -0.55
    RepeatedField
    -0.55
    qrstuvwxyz
    -0.54
     demen
    -0.53
    ThroughAttribute
    -0.52
    oughby
    -0.52
     BrowserModule
    -0.52
    avits
    -0.52
    POSITIVE LOGITS
    Predecesor
    0.53
    träge
    0.48
    BlockPos
    0.45
    olk
    0.44
     Andersen
    0.44
    oxin
    0.44
    лтемелер
    0.44
    NOS
    0.43
     HttpStatusCode
    0.43
    tième
    0.42
    Activations Density 1.247%

    No Known Activations