© 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. 12712
    Prev
    Next
    INDEX
    Explanations

    references to the term "Roman."

    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
     Efq
    -1.48
     Monfieur
    -1.30
     myſelf
    -1.27
     itſelf
    -1.21
     Theſe
    -1.19
     Anſ
    -1.18
     Reſ
    -1.14
     ſeveral
    -1.12
     himſelf
    -1.11
     theſe
    -1.07
    POSITIVE LOGITS
     Rom
    1.55
    Rom
    1.43
     ROM
    1.42
     rom
    1.35
     Romero
    1.27
    ROM
    1.27
     Roman
    1.27
    rom
    1.23
     Romano
    1.14
    Roman
    1.12
    Activations Density 0.013%

    No Known Activations