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. 31287
    Prev
    Next
    INDEX
    Explanations

    capitalized last names, particularly authors cited within a document

    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
    FunctionFlags
    -0.77
    ArgumentParser
    -0.67
     CommandType
    -0.65
    cticut
    -0.63
     MainAxisSize
    -0.63
    ienki
    -0.60
    owulf
    -0.60
     Fas
    -0.59
    OGND
    -0.59
     bim
    -0.59
    POSITIVE LOGITS
     Donny
    0.82
     Stich
    0.78
     Trey
    0.77
     Blau
    0.77
    IsContent
    0.77
     Leeuwen
    0.75
     Ishi
    0.73
    Nak
    0.73
     Samar
    0.73
     optic
    0.72
    Activations Density 0.396%

    No Known Activations