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. 31403
    Prev
    Next
    INDEX
    Explanations

    the phrase "very much"

    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
     tatuajes
    -0.68
    CodeAnalysis
    -0.68
    достатки
    -0.67
     Steinberg
    -0.67
     juſ
    -0.66
     کوت
    -0.66
    tehenden
    -0.65
    eapple
    -0.65
    ihnachts
    -0.65
    luß
    -0.63
    POSITIVE LOGITS
     незавершена
    0.73
    CloseOperation
    0.73
    typeparam
    0.63
     opio
    0.63
     estimés
    0.60
    CopyWith
    0.60
    PreferredItem
    0.59
    rootScope
    0.59
     fok
    0.59
    medriver
    0.58
    Activations Density 0.004%

    No Known Activations