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. 9-RES-MATRYOSHKA-DC
    4. 16618
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with plus signs representing charged ions

    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
    AccountName
    -0.69
    Grüsse
    -0.62
    AMIENTO
    -0.62
    wige
    -0.62
    üdis
    -0.61
    Lesen
    -0.61
    достатки
    -0.60
    BibitemShut
    -0.60
     IBRARY
    -0.60
    bited
    -0.59
    POSITIVE LOGITS
    Datuak
    0.73
    preduce
    0.67
    opardy
    0.63
     jedi
    0.61
    Mozart
    0.60
     مرئيه
    0.59
     kaupung
    0.58
     veterinario
    0.58
     Heuer
    0.57
     Kanpur
    0.57
    Activations Density 0.005%

    No Known Activations