© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    references to the evaluation of a specific approximation method used in describing physical phenomena

    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
    RectangleBorder
    -1.13
    mybatisplus
    -0.92
    XMLSchema
    -0.90
     nahilalakip
    -0.84
     للاسماء
    -0.78
    ImageContext
    -0.78
    ChildScrollView
    -0.77
     MainAxisSize
    -0.72
    PickerController
    -0.71
    expandindo
    -0.71
    POSITIVE LOGITS
     however
    0.85
     meanwhile
    0.81
     inoltre
    0.71
     zaś
    0.67
     însă
    0.67
     also
    0.65
     therefore
    0.63
     però
    0.63
    however
    0.63
     natomiast
    0.63
    Activations Density 0.313%

    No Known Activations