© 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. 2-RES-MATRYOSHKA-DC
    7. 5163
    Prev
    Next
    INDEX
    Explanations

    references to measurements of layer or film thickness in the context of material deposition or fabrication processes

    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
     long
    -0.71
     slow
    -0.66
     largas
    -0.66
     narrow
    -0.65
    slow
    -0.63
    Chham
    -0.61
    avigation
    -0.61
     skinny
    -0.59
    long
    -0.59
    iostream
    -0.57
    POSITIVE LOGITS
     thickness
    2.55
     Thickness
    2.36
     thicknesses
    2.22
    thickness
    2.11
    Thickness
    1.95
     espesor
    1.39
    厚度
    1.30
    épaisseur
    1.17
     thicker
    1.15
     thicken
    1.12
    Activations Density 0.010%

    No Known Activations