© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1714
    Prev
    Next
    INDEX
    Explanations

    mentions of economics, financial institutions and money

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    uxxxx
    -0.59
    :✨
    -0.59
    Geplaatst
    -0.59
    etano
    -0.58
     Khrushchev
    -0.56
    DockStyle
    -0.56
     виправивши
    -0.55
     resourceCulture
    -0.54
     miel
    -0.52
    setVerticalGroup
    -0.52
    POSITIVE LOGITS
     bank
    2.03
     banks
    1.87
     banking
    1.81
     Bank
    1.79
    bank
    1.73
    Bank
    1.66
     BANK
    1.65
     Banking
    1.60
     bankers
    1.55
     Banks
    1.54
    Activations Density 0.703%

    No Known Activations