© 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. 21129
    Prev
    Next
    INDEX
    Explanations

    significant instances of specific pronouns and articles in 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
     ujednoznacz
    -0.53
     panahon
    -0.52
    avut
    -0.52
     forState
    -0.50
     Skrill
    -0.50
     Normdatei
    -0.49
    EndContext
    -0.49
     Bloomsbury
    -0.47
    Bissau
    -0.47
    로그램
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.72
     TextAppearance
    0.62
     незавершена
    0.60
    IsMutable
    0.57
    发表于
    0.56
    исленность
    0.54
     healthiest
    0.53
    Portail
    0.53
    reactivex
    0.53
    WriteByte
    0.52
    Activations Density 0.001%

    No Known Activations