© 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. 26831
    Prev
    Next
    INDEX
    Explanations

    words related to surprise or unexpected outcomes

    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
    ArrowToggle
    -0.72
    Autoritní
    -0.64
     weird
    -0.63
    Nero
    -0.63
     bizarre
    -0.62
    .*")]
    -0.62
    Controllo
    -0.62
     crazy
    -0.61
    weird
    -0.60
     Kat
    -0.60
    POSITIVE LOGITS
     Surprise
    0.88
    ***************/
    0.81
    Surprise
    0.81
     surprise
    0.74
     surprises
    0.72
    surprise
    0.69
    prises
    0.68
     Suf
    0.68
    AddTagHelper
    0.68
     XCTest
    0.68
    Activations Density 0.010%

    No Known Activations