© 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. 21139
    Prev
    Next
    INDEX
    Explanations

    references to pixel counts and definitions in imaging contexts

    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
    SpringBootTest
    -0.90
     acoper
    -0.83
     MHC
    -0.83
     Wikimedijinoj
    -0.82
     kasarigan
    -0.80
     EconPapers
    -0.78
    Boas
    -0.77
    ंदीखरीदारी
    -0.77
     doInBackground
    -0.77
    +#+
    -0.75
    POSITIVE LOGITS
     pixels
    1.46
     Pixels
    1.44
     Pixel
    1.41
     pixel
    1.34
    pixels
    1.34
    PIXEL
    1.25
    pixel
    1.16
    Pixels
    1.13
    Pixel
    1.12
    ixel
    1.02
    Activations Density 0.004%

    No Known Activations