© 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. 26953
    Prev
    Next
    INDEX
    Explanations

    words related to brazing in manufacturing contexts

    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
    Negative Logits
    %");
    -0.99
    %</
    -0.94
    %")
    -0.93
     Turnpike
    -0.88
    .}}
    -0.86
     Infórmanos
    -0.84
     Jagger
    -0.84
    .'</
    -0.84
    %"),
    -0.84
     Defects
    -0.83
    POSITIVE LOGITS
     Bra
    1.51
     bra
    1.37
    Bra
    1.34
     Braxton
    1.32
     Bradshaw
    1.30
    bra
    1.30
     Bragg
    1.26
     BRA
    1.25
     bras
    1.16
     Bracken
    1.13
    Activations Density 0.043%

    No Known Activations