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. 2-RES-MATRYOSHKA-DC
    4. 15
    Prev
    Next
    INDEX
    Explanations

    references to Volkswagen vehicles, automobiles, or related terms

    oai_token-act-pair · gpt-4.1-nano
    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
    InjectAttribute
    -0.89
     ostavi
    -0.83
    SourceChecksum
    -0.74
    PropertyChanging
    -0.73
     Gerente
    -0.73
    rungsseite
    -0.72
    ExtendWith
    -0.72
     Luncheon
    -0.68
    :✨
    -0.68
     Apprenticeship
    -0.68
    POSITIVE LOGITS
     States
    1.50
     USA
    1.46
     US
    1.34
     America
    1.32
     American
    1.30
     United
    1.25
     states
    1.25
    States
    1.23
     Federal
    1.20
    states
    1.18
    Activations Density 6.771%

    No Known Activations