© 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. 6-RES-MATRYOSHKA-DC
    7. 1345
    Prev
    Next
    INDEX
    Explanations

    the word "load" and its variants along with nearby related words.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     plebis
    -0.90
    بوابة
    -0.83
     chives
    -0.80
    /*
    -0.79
    elesai
    -0.77
     sellado
    -0.77
     bise
    -0.76
    Jereo
    -0.74
     MATHEMAT
    -0.74
    Namara
    -0.73
    POSITIVE LOGITS
     load
    2.02
     Load
    1.98
    load
    1.86
     loading
    1.80
    Load
    1.79
     LOAD
    1.79
    LOAD
    1.78
     loads
    1.76
    loads
    1.73
     Loads
    1.72
    Activations Density 0.303%

    No Known Activations