© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15397
    Prev
    Next
    INDEX
    Explanations

    mentions of measurement units and numerical data related to dosages

    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
     Baillargeon
    -0.65
     ویکی‌پدیای
    -0.63
    órmulas
    -0.60
    tagHelperRunner
    -0.59
     Aceh
    -0.59
     Vikipedi
    -0.59
     gata
    -0.58
    Herz
    -0.57
     Affairs
    -0.56
     Hennessy
    -0.56
    POSITIVE LOGITS
    toma
    4.25
    tomas
    2.47
     toma
    1.43
    Toma
    1.25
     Toma
    1.09
     tomas
    0.72
    tomi
    0.63
    InjectMocks
    0.62
    tomat
    0.61
    Referències
    0.57
    Activations Density 0.000%

    No Known Activations