© 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. 18877
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associated usage in context

    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
     contextLoads
    -0.69
    éfonos
    -0.64
    ValueStyle
    -0.59
    ſelves
    -0.54
     others
    -0.53
     gant
    -0.52
    lägen
    -0.52
    DataAdapter
    -0.52
    ryk
    -0.52
    ViewFeatures
    -0.51
    POSITIVE LOGITS
     AssemblyCulture
    0.65
     EconPapers
    0.65
     JpaRepository
    0.59
     bParam
    0.56
     RoutedEventArgs
    0.52
     TextAppearance
    0.52
     Walkover
    0.52
    campista
    0.50
     }));
    0.50
    يكب
    0.50
    Activations Density 0.231%

    No Known Activations