© 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. 20292
    Prev
    Next
    INDEX
    Explanations

    specific symbols or formatting elements in the text

    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
    ↵↵
    -0.68
    -
    -0.57
    tr
    -0.54
     -
    -0.52
    y
    -0.52
    :
    -0.49
    ...
    -0.48
    Desde
    -0.48
     find
    -0.47
    us
    -0.47
    POSITIVE LOGITS
    ibr
    1.30
     purpoſe
    1.23
     myſelf
    1.21
     reaſon
    1.14
     houſe
    1.14
     Majefty
    1.14
     ſeveral
    1.13
     pleaſure
    1.13
     raiſ
    1.11
     Anſ
    1.10
    Activations Density 0.000%

    No Known Activations