© 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. 17151
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or strong emotion

    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
     myſelf
    -0.68
     useRouter
    -0.59
     chofe
    -0.59
     Münch
    -0.59
    unico
    -0.58
    Usted
    -0.58
    脚注の使い方
    -0.58
    ագրություններ
    -0.57
     houſe
    -0.57
    Yeet
    -0.57
    POSITIVE LOGITS
     Oh
    0.87
     oh
    0.81
    metheus
    0.79
    Oh
    0.78
    toh
    0.77
     OH
    0.75
    *}[
    0.73
    /**
    0.72
     TextAppearance
    0.69
     Mish
    0.69
    Activations Density 0.008%

    No Known Activations