© 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. 2-RES-MATRYOSHKA-DC
    7. 2741
    Prev
    Next
    INDEX
    Explanations

    segments describing image processing steps, including extracting regions of interest, resizing, and converting color spaces

    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
     détach
    -0.52
     puissiez
    -0.49
    glTexCoord
    -0.48
     arbejds
    -0.48
     étag
    -0.48
     segno
    -0.47
     tjän
    -0.46
     sexuales
    -0.46
     Winaray
    -0.45
    Synonymes
    -0.45
    POSITIVE LOGITS
     }}"></
    0.68
    OrNil
    0.64
    WindowConstants
    0.62
     XHTML
    0.61
    setContentView
    0.59
    InputBorder
    0.59
    listdir
    0.58
    makeText
    0.57
     externi
    0.57
    bular
    0.56
    Activations Density 1.058%

    No Known Activations