© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9891
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their properties in 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
    州市
    -0.59
    UIControlState
    -0.54
    calipsis
    -0.50
     singola
    -0.49
    otis
    -0.49
    audiovisuel
    -0.48
    heça
    -0.47
     />\
    -0.46
    hungry
    -0.46
     ubicada
    -0.45
    POSITIVE LOGITS
     already
    0.59
    JvmStatic
    0.58
     getRule
    0.58
    SwingConstants
    0.57
     AssemblyVersion
    0.55
    〢
    0.54
     Faraday
    0.54
    principalTable
    0.54
     @"/
    0.53
    Predecesor
    0.52
    Activations Density 0.544%

    No Known Activations