© 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. 14266
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or surprise

    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
     referenties
    -0.84
    CppMethod
    -0.67
    updateUI
    -0.61
     snippetHide
    -0.56
    PhysRev
    -0.55
     imo
    -0.54
     IMO
    -0.54
    NameInMap
    -0.54
     ?',
    -0.52
     feel
    -0.51
    POSITIVE LOGITS
    Tikang
    0.73
     multer
    0.65
    multer
    0.55
    хьтан
    0.53
     teased
    0.52
     rivalry
    0.52
     relativa
    0.52
     teasing
    0.47
    roni
    0.46
     joked
    0.46
    Activations Density 0.208%

    No Known Activations