© 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. 17047
    Prev
    Next
    INDEX
    Explanations

    the repetition of a specific concept or term throughout the text

    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
    odore
    -0.58
    볍
    -0.57
     polvere
    -0.57
     coû
    -0.56
     réaliste
    -0.56
     Ghosh
    -0.56
     subterrá
    -0.56
     goû
    -0.55
     lusso
    -0.55
     conmigo
    -0.55
    POSITIVE LOGITS
    ChildScrollView
    0.65
    RefNanny
    0.61
    
    0.59
    İstinadlar
    0.59
    FunctionFlags
    0.57
     Schwab
    0.56
     Sef
    0.56
    XmlAccessType
    0.55
    ContentAsync
    0.54
     COB
    0.54
    Activations Density 0.002%

    No Known Activations