© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    terms related to occupancy or occupation within systems

    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
     Alvarado
    -0.68
     Atwood
    -0.66
     Herod
    -0.66
     päiv
    -0.63
    FORMA
    -0.62
     marad
    -0.61
     szár
    -0.60
     øns
    -0.60
    Bi
    -0.60
    Parameteri
    -0.59
    POSITIVE LOGITS
     occupa
    1.41
     OCCUP
    1.34
     occup
    1.30
     Occup
    1.28
    occup
    1.21
     occupy
    1.20
     Occupations
    1.19
    Occup
    1.18
     occupied
    1.15
    occupied
    1.15
    Activations Density 0.013%

    No Known Activations