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. 14168
    Prev
    Next
    INDEX
    Explanations

    descriptions of speaker or audio equipment features

    oai_token-act-pair · gemini-2.0-flash

    technical text

    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
     ErrIntOverflow
    -0.88
    Personendaten
    -0.74
     informée
    -0.72
    دانشنامهٔ
    -0.70
     ویکی‌پدی
    -0.69
     BrowserModule
    -0.66
     AppModule
    -0.66
    AndroidJUnit
    -0.64
     تانيه
    -0.63
    chymal
    -0.63
    POSITIVE LOGITS
    UrlResolution
    0.50
     Marino
    0.46
     double
    0.45
     mid
    0.44
    netty
    0.42
    ény
    0.42
    kait
    0.41
    manteau
    0.41
     dia
    0.41
     sen
    0.40
    Activations Density 0.636%

    No Known Activations