© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16793
    Prev
    Next
    INDEX
    Explanations

    the category classification of films and their relevant details

    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
    forhold
    -0.57
     year
    -0.50
    Izvori
    -0.46
    hlon
    -0.46
    GIVEREF
    -0.44
    bedaan
    -0.43
     Year
    -0.42
    gnu
    -0.42
     scénario
    -0.40
     No
    -0.40
    POSITIVE LOGITS
    出版年
    0.86
     EconPapers
    0.82
     autorytatywna
    0.81
    Tikang
    0.80
     disambiguazione
    0.79
     Paglinawan
    0.75
     ostavi
    0.73
    Pranala
    0.72
    SizeMode
    0.72
     wireType
    0.70
    Activations Density 0.008%

    No Known Activations