© 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. 14962
    Prev
    Next
    INDEX
    Explanations

    the prefix "re" and its variations indicating repetition or return actions

    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
    httphttps
    -0.74
    theless
    -0.65
    AutoField
    -0.63
    zeka
    -0.63
     backlash
    -0.63
       
    -0.63
    MigrationBuilder
    -0.62
     sappi
    -0.61
    而言
    -0.60
    GenerationType
    -0.60
    POSITIVE LOGITS
     öss
    0.68
    inander
    0.66
     knex
    0.60
    knex
    0.59
    ężczy
    0.57
    WithEmail
    0.57
     vermelhas
    0.57
    Zunanje
    0.56
    osene
    0.56
     put
    0.56
    Activations Density 0.007%

    No Known Activations