Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 22352
    Prev
    Next
    INDEX
    Explanations

    terms related to sealing mechanisms in electrical connections

    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
     Granger
    -0.75
     Asbury
    -0.75
    rdoba
    -0.68
    Rüyada
    -0.68
     Bantu
    -0.68
     Kuru
    -0.67
     Westfield
    -0.67
     Giovan
    -0.64
     Lexington
    -0.63
     escol
    -0.61
    POSITIVE LOGITS
     seal
    1.70
     seals
    1.61
     sealed
    1.57
     Seal
    1.56
    sealed
    1.55
     sealing
    1.54
     Seals
    1.50
     Sealing
    1.47
    Seal
    1.45
     Sealed
    1.44
    Activations Density 0.006%

    No Known Activations