© 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. 0-RES-MATRYOSHKA-DC
    7. 12299
    Prev
    Next
    INDEX
    Explanations

    references to implementation strategies used in research and practice

    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
     strategic
    -1.17
    strategic
    -1.16
    Strategic
    -1.10
     Strategic
    -0.98
     stratégique
    -0.81
     Strategy
    -0.79
     strategy
    -0.79
    战略
    -0.77
     estratégica
    -0.74
    Strategy
    -0.70
    POSITIVE LOGITS
     strategies
    1.52
     Strategies
    1.40
    Strategies
    1.37
    strategies
    1.25
     estrategias
    0.86
     stratégies
    0.77
     tips
    0.75
    Рекомен
    0.66
    Tips
    0.64
     ItemStack
    0.61
    Activations Density 0.004%

    No Known Activations