© 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. 0-RES-MATRYOSHKA-DC
    7. 10706
    Prev
    Next
    INDEX
    Explanations

    aspects related to hardware components and processing hardware

    oai_token-act-pair · gpt-4.1-nano
    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
    Not in Any Lists

    No Comments

    Negative Logits
     primer
    -1.05
     Primer
    -0.85
     PRIMER
    -0.84
     primers
    -0.84
    primer
    -0.81
    Primer
    -0.79
    PRIMER
    -0.76
    хьтан
    -0.70
     backing
    -0.66
     propOrder
    -0.63
    POSITIVE LOGITS
     hardware
    1.31
    hardware
    1.14
     Hardware
    1.13
    Hardware
    1.09
    硬件
    0.90
    HARDWARE
    0.81
    mybatisplus
    0.63
     Dunbar
    0.56
     keres
    0.54
     drum
    0.52
    Activations Density 0.002%

    No Known Activations