© 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. 5834
    Prev
    Next
    INDEX
    Explanations

    references to the system or programming environment

    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
    saraba
    -0.85
    adə
    -0.73
    EndInit
    -0.69
     الحره
    -0.68
    openSession
    -0.68
    StoryboardSegue
    -0.68
    queryInterface
    -0.66
    AutoField
    -0.64
    VideoCapture
    -0.63
    Sklici
    -0.62
    POSITIVE LOGITS
    System
    2.14
     System
    1.75
     SYSTEM
    1.01
     Systemic
    0.88
    SYSTEM
    0.81
     systemic
    0.81
    system
    0.78
    ystem
    0.74
     Syst
    0.59
    Syst
    0.57
    Activations Density 0.023%

    No Known Activations