© 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. 21126
    Prev
    Next
    INDEX
    Explanations

    references to image file formats, particularly JPEG

    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
     saites
    -0.84
    Portale
    -0.75
    unittest
    -0.60
    ambilan
    -0.57
     Fab
    -0.56
     createSlice
    -0.55
    бия
    -0.54
    Choi
    -0.54
    columbia
    -0.54
     portail
    -0.54
    POSITIVE LOGITS
    jpeg
    1.51
     jpeg
    1.36
     JPEG
    1.31
    JPEG
    1.15
     PEP
    0.93
    endphp
    0.93
     Samb
    0.81
     OAS
    0.81
     Pequ
    0.79
     Koran
    0.77
    Activations Density 0.001%

    No Known Activations