© 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. 14953
    Prev
    Next
    INDEX
    Explanations

    instances of first occurrences or first-time achievements

    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
     autorytatywna
    -0.71
    Portale
    -0.70
     estekak
    -0.70
    TypedDataSet
    -0.69
    rawDesc
    -0.68
    Lähteet
    -0.68
    parsedMessage
    -0.68
    VIER
    -0.67
     BoxDecoration
    -0.66
     يتيمه
    -0.66
    POSITIVE LOGITS
     pertama
    0.56
     puis
    0.48
    率先
    0.47
     developed
    0.44
     tiên
    0.44
     zuerst
    0.43
     sorti
    0.42
    صدر
    0.42
     ensimmä
    0.41
     before
    0.41
    Activations Density 0.079%

    No Known Activations