© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5432
    Prev
    Next
    INDEX
    Explanations

    references to game mechanics and character attributes related to healing, damage mitigation, and boss encounters

    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
    thodoxy
    -0.62
     समीक्षक
    -0.60
    calientes
    -0.54
    
    -0.53
    getWriter
    -0.53
     الصيف
    -0.52
    Cordialement
    -0.52
    voltaic
    -0.51
     Filho
    -0.51
    SqlDataReader
    -0.50
    POSITIVE LOGITS
     boss
    1.10
     enemies
    1.00
     enemy
    1.00
     bosses
    0.94
     Boss
    0.90
    boss
    0.84
     Enemy
    0.82
    Boss
    0.82
     Enemies
    0.82
     BOSS
    0.81
    Activations Density 0.222%

    No Known Activations