© 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. 11741
    Prev
    Next
    INDEX
    Explanations

    special formatting or unique characters 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
    hető
    -0.44
    ret
    -0.42
    .
    -0.39
    ンズ
    -0.38
    ref
    -0.35
    ﾉ
    -0.35
    羹
    -0.35
    Realm
    -0.34
     CONDITIONS
    -0.33
    react
    -0.33
    POSITIVE LOGITS
     kasarigan
    1.09
    Enllaces
    1.03
     myſelf
    1.02
    Datuak
    1.00
     itſelf
    0.96
    Autoritní
    0.96
    ContentAsync
    0.94
     autorytatywna
    0.94
     مشين
    0.93
    #+#
    0.93
    Activations Density 0.019%

    No Known Activations