© 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. 15693
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unprecedented" and phrases that suggest significant or exceptional occurrences

    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
     CGSize
    -0.58
     /\.(
    -0.56
     Guildford
    -0.48
     Eks
    -0.47
    middels
    -0.45
     Económica
    -0.44
    AccessorTable
    -0.44
    CloseOperation
    -0.42
     resold
    -0.42
     sapon
    -0.42
    POSITIVE LOGITS
     unprecedented
    0.85
    precedented
    0.77
     للاسماء
    0.71
    Bronnen
    0.67
    unknownFields
    0.64
    bleven
    0.63
    principalColumn
    0.62
    lässlich
    0.61
    nessed
    0.58
    kowania
    0.58
    Activations Density 0.032%

    No Known Activations