© 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. 12-RES-MATRYOSHKA-DC
    7. 3789
    Prev
    Next
    INDEX
    Explanations

    references to banking institutions and related financial 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
    Not in Any Lists

    No Comments

    Negative Logits
    PhysRev
    -0.79
     externi
    -0.74
    YourGuide
    -0.72
    sut
    -0.72
     Hirsch
    -0.71
    ^(@)
    -0.68
    volo
    -0.68
    ymce
    -0.68
     Bucure
    -0.68
     CTE
    -0.65
    POSITIVE LOGITS
     banks
    1.63
     Banks
    1.62
    Banks
    1.60
     BANK
    1.59
     Bank
    1.58
     bank
    1.55
    Bank
    1.50
    bank
    1.46
    BANK
    1.45
     BANKS
    1.42
    Activations Density 0.018%

    No Known Activations