© 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. 2-RES-MATRYOSHKA-DC
    7. 3530
    Prev
    Next
    INDEX
    Explanations

    mentions of ATM or bank cards

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heart
    -1.27
    heart
    -1.08
    HEART
    -1.02
     Heart
    -1.02
    Heart
    -0.98
     HEART
    -0.96
     hearts
    -0.89
    hearts
    -0.81
     hart
    -0.75
     corazón
    -0.74
    POSITIVE LOGITS
     card
    3.27
     Card
    3.14
     cards
    3.05
    Card
    2.97
    card
    2.94
     Cards
    2.94
    cards
    2.66
    Cards
    2.66
     CARD
    2.66
     CARDS
    2.58
    Activations Density 0.048%

    No Known Activations