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. 12-RES-MATRYOSHKA-DC
    4. 66
    Prev
    Next
    INDEX
    Explanations

    categories or classifications related to individuals, particularly within the context of sports or awards

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Искәрмәләр
    -0.81
    AddTagHelper
    -0.75
    ContentAlignment
    -0.69
     مرئيه
    -0.68
    InputTagHelper
    -0.67
    énario
    -0.66
     kasarigan
    -0.66
    Lähteet
    -0.66
    IntoConstraints
    -0.66
     становника
    -0.59
    POSITIVE LOGITS
    ⓘ
    0.78
    Portail
    0.63
     contextLoads
    0.57
    Portale
    0.56
    ANDE
    0.54
     Kategorie
    0.51
     Category
    0.50
    KURZBESCHREIBUNG
    0.49
    Datuak
    0.48
    FunctionFlags
    0.47
    Activations Density 1.181%

    No Known Activations