© 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. 31924
    Prev
    Next
    INDEX
    Explanations

    financial terms, specifically relating to monetary values or currency

    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
     pinulongan
    -1.00
     Efq
    -0.98
     vectorstock
    -0.97
    ſelf
    -0.97
     Theſe
    -0.95
     chofe
    -0.94
     lenker
    -0.94
     itſelf
    -0.93
     preſent
    -0.92
     greateſt
    -0.91
    POSITIVE LOGITS
     I
    0.63
     y
    0.59
     N
    0.57
     &
    0.54
     F
    0.52
    GraphicsUnit
    0.51
     =
    0.49
    ;&
    0.48
     D
    0.48
     lí
    0.48
    Activations Density 0.006%

    No Known Activations