© 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. 0-RES-MATRYOSHKA-DC
    7. 15097
    Prev
    Next
    INDEX
    Explanations

    references to improvements or enhancements

    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
     poor
    -0.81
    
    -0.80
     BoxFit
    -0.79
     enhance
    -0.75
    StoryboardSegue
    -0.72
    Poor
    -0.71
    fillType
    -0.69
     Poor
    -0.69
    ########.
    -0.68
    حوالہ
    -0.68
    POSITIVE LOGITS
     improvements
    1.91
     Improvements
    1.80
    Improvements
    1.67
     mejoras
    1.00
     enhancements
    0.83
     upgrades
    0.81
     refinements
    0.78
     advancements
    0.78
     IMPROV
    0.78
     Upgrades
    0.72
    Activations Density 0.004%

    No Known Activations