© 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. 5992
    Prev
    Next
    INDEX
    Explanations

    references to reward symbols, bonus features, and related casino game elements

    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
    DeleteBehavior
    -0.78
     متعلقه
    -0.69
     pstmt
    -0.60
    SpringBootTest
    -0.60
    帖最后由
    -0.57
     estekak
    -0.56
    httphttps
    -0.56
     ویکی‌پدیا
    -0.56
    DrawerToggle
    -0.56
    CloseOperation
    -0.56
    POSITIVE LOGITS
     reward
    2.53
     rewards
    2.38
     Reward
    2.31
     bonus
    2.17
     Rewards
    2.16
     prize
    2.09
    reward
    2.06
    Reward
    2.05
     Bonus
    1.98
     prizes
    1.98
    Activations Density 0.093%

    No Known Activations