© 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. 20727
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or amazement regarding people's actions and beliefs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Vikipedi
    -0.50
     تضيفلها
    -0.50
    +#+
    -0.47
     ters
    -0.47
    ]();
    -0.47
    tamina
    -0.46
    “…
    -0.46
     dem
    -0.45
    ="$(
    -0.45
     frapp
    -0.45
    POSITIVE LOGITS
    lewati
    0.64
     Económica
    0.64
     LIRE
    0.62
     survives
    0.61
     sobrevi
    0.60
    urlpatterns
    0.59
     umana
    0.57
     pogod
    0.57
    Portale
    0.56
     esternos
    0.55
    Activations Density 0.084%

    No Known Activations