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. 8-RES-MATRYOSHKA-DC
    4. 31145
    Prev
    Next
    INDEX
    Explanations

    numerical digits within text or equations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
     виправивши
    -0.73
    Rui
    -0.70
     betweenstory
    -0.70
    ountain
    -0.69
    HostException
    -0.69
     Tully
    -0.65
    WebVitals
    -0.65
    kku
    -0.63
    __[
    -0.62
    umba
    -0.62
    POSITIVE LOGITS
     Hadid
    0.68
     Шар
    0.57
     AppCompatTheme
    0.56
    dS
    0.56
    rawDesc
    0.56
    sapp
    0.55
     σχε
    0.54
    itemid
    0.54
     Redesign
    0.54
    !("{}",
    0.54
    Activations Density 0.143%

    No Known Activations