© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    features related to Gaussian kernels and their applications in image processing, smoothing, and noise reduction

    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
     itſelf
    -1.18
    Datuak
    -1.12
     myſelf
    -1.10
    存于互联网档案馆
    -1.03
     للمعارف
    -0.99
    NUMX
    -0.98
     ModelRenderer
    -0.98
    ſelf
    -0.93
     ་་
    -0.93
    WebServlet
    -0.92
    POSITIVE LOGITS
     Gaussian
    0.62
    matic
    0.60
     Bass
    0.58
    Gaussian
    0.57
    ionic
    0.56
     bass
    0.55
     chia
    0.54
    semantic
    0.54
     acoustic
    0.54
    Bass
    0.53
    Activations Density 0.822%

    No Known Activations