© 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. 20419
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "each" or "a" indicating enumeration or unspecified quantity

    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
    ulele
    -0.81
     архивлан
    -0.73
    AndEndTag
    -0.73
    脚注の使い方
    -0.72
    Personensuche
    -0.71
     Mosca
    -0.71
    Бахар
    -0.71
     auroit
    -0.71
     SwitchCompat
    -0.70
     feroit
    -0.70
    POSITIVE LOGITS
    inigungs
    0.48
    
    0.48
     Mrs
    0.47
    findpost
    0.46
     McGu
    0.46
     H
    0.45
    nhold
    0.45
     aren
    0.45
     "
    0.44
     оформ
    0.43
    Activations Density 0.014%

    No Known Activations