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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5087
    Prev
    Next
    INDEX
    Explanations

    references to substrates and layers in semiconductor manufacturing processes

    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
    endpush
    -0.54
    NoSuchAlgorithm
    -0.47
     Auss
    -0.46
    InteropServices
    -0.44
    zaw
    -0.44
     zaw
    -0.43
     ده
    -0.43
    Fernseh
    -0.43
    connectionString
    -0.43
     period
    -0.42
    POSITIVE LOGITS
     substrates
    1.05
     substrate
    1.00
    Substrate
    0.95
     Substrate
    0.92
     Surfaces
    0.88
    WithIOException
    0.87
    substrate
    0.82
    SharedCtor
    0.78
    strates
    0.77
     utafitiHapana
    0.76
    Activations Density 0.505%

    No Known Activations