© 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. 9415
    Prev
    Next
    INDEX
    Explanations

    terms related to labor and workforce issues

    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
    sunter
    -0.77
    smöglichkeiten
    -0.73
     Thule
    -0.72
     Inverness
    -0.70
     pickle
    -0.68
     encyclo
    -0.67
     antlers
    -0.65
     LEX
    -0.65
    bootstrapcdn
    -0.65
     Lübeck
    -0.65
    POSITIVE LOGITS
     Labor
    1.39
     labor
    1.37
    labor
    1.34
     LABOR
    1.32
    Labor
    1.28
     labors
    1.23
    LABOR
    1.17
     laboring
    1.15
     labour
    1.14
     Labour
    1.05
    Activations Density 0.006%

    No Known Activations