© 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. 20477
    Prev
    Next
    INDEX
    Explanations

    terms related to quantum physics and specifically the Bose-Einstein condensate

    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
     Patricio
    -0.65
     barnen
    -0.63
     Miners
    -0.63
    RequestMethod
    -0.62
     Zier
    -0.62
     mourut
    -0.61
    rungsseite
    -0.60
    +#+#
    -0.60
    Pato
    -0.59
     escul
    -0.59
    POSITIVE LOGITS
     Bose
    1.13
    Bose
    1.11
     bose
    0.85
     bosons
    0.78
    saraba
    0.72
    kháu
    0.71
     linkovi
    0.70
     GetEnumerator
    0.68
    bose
    0.68
    цездатний
    0.68
    Activations Density 0.003%

    No Known Activations