© 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. 1-RES-MATRYOSHKA-DC
    7. 998
    Prev
    Next
    INDEX
    Explanations

    references to specific hardware issues, configurations, and technical troubleshooting steps

    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
     its
    -1.05
    Its
    -1.03
     Its
    -0.99
     kanyang
    -0.94
     Himself
    -0.94
     himself
    -0.94
    himself
    -0.91
    だが
    -0.86
     Itself
    -0.85
    だったが
    -0.85
    POSITIVE LOGITS
     your
    2.83
    your
    2.48
    Your
    2.34
     Your
    2.30
    YOUR
    2.06
     YOUR
    1.94
     votre
    1.74
    你的
    1.61
    votre
    1.51
    Votre
    1.48
    Activations Density 0.101%

    No Known Activations