© 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. 23715
    Prev
    Next
    INDEX
    Explanations

    references to formal documents or legal agreements, particularly charters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    piecz
    -0.76
     Etrus
    -0.75
     Koy
    -0.75
     Jof
    -0.73
     Serbs
    -0.73
    Vul
    -0.71
    okovic
    -0.70
    gemene
    -0.69
    ändler
    -0.68
    flink
    -0.68
    POSITIVE LOGITS
     Charter
    1.61
    Charter
    1.51
     charter
    1.42
     Charters
    1.33
    charter
    1.24
     charters
    1.21
    Portail
    0.97
     Carta
    0.77
     chartered
    0.77
    cupa
    0.75
    Activations Density 0.001%

    No Known Activations