© 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. 32420
    Prev
    Next
    INDEX
    Explanations

    expressions of amazement or admiration

    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
    ELDS
    -0.59
    ークル
    -0.57
     wenn
    -0.54
    unusual
    -0.54
     Humor
    -0.54
    ISTRO
    -0.54
    ContentAsync
    -0.53
    baidu
    -0.53
    skosten
    -0.53
    uyla
    -0.53
    POSITIVE LOGITS
     feats
    0.90
    amazing
    0.90
     Incredible
    0.90
     incroy
    0.86
    Amazing
    0.84
     Amazing
    0.83
     amazing
    0.82
     incredi
    0.82
    AMAZING
    0.82
     Lein
    0.81
    Activations Density 0.024%

    No Known Activations