© 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. 229
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical phenomena and concepts

    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
     noDo
    -0.49
    gdala
    -0.44
     Altman
    -0.41
    siasme
    -0.41
     Україні
    -0.41
     éclair
    -0.40
     meglio
    -0.40
     geng
    -0.40
     passent
    -0.40
     дорога
    -0.40
    POSITIVE LOGITS
     physical
    4.09
     Physical
    3.94
    Physical
    3.83
    physical
    3.83
     Phys
    3.58
     physically
    3.52
     PHYSICAL
    3.50
    Phys
    3.41
    PHYSICAL
    3.39
     phys
    3.36
    Activations Density 1.092%

    No Known Activations