© 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. 30677
    Prev
    Next
    INDEX
    Explanations

    references to Bitcoin and its related terms

    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
     Sche
    -0.63
    liferay
    -0.59
     Milky
    -0.56
    Parcelable
    -0.56
     lot
    -0.53
    t
    -0.52
    Salta
    -0.52
    _
    -0.52
     space
    -0.51
    mathcal
    -0.50
    POSITIVE LOGITS
     bitcoins
    1.34
     bitcoin
    1.31
     Bitcoin
    1.26
    Bitcoin
    1.26
    bitcoin
    1.13
     BTC
    0.93
    BTC
    0.91
     btc
    0.87
    比特币
    0.82
     grève
    0.77
    Activations Density 0.001%

    No Known Activations