© 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. 12-RES-MATRYOSHKA-DC
    7. 4021
    Prev
    Next
    INDEX
    Explanations

    terms related to physics, specifically referencing publications and their citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.77
    strual
    -0.74
    opardy
    -0.72
    gouv
    -0.72
    zbęd
    -0.71
     eiffel
    -0.69
    makeConstraints
    -0.68
     tärke
    -0.68
    fromCharCode
    -0.68
    nsf
    -0.67
    POSITIVE LOGITS
     Phys
    1.16
     phys
    0.96
    Phys
    0.95
    phys
    0.80
     PHYS
    0.73
    ocks
    0.70
    ysis
    0.66
    PHYS
    0.65
    Kyr
    0.63
    }\]
    0.61
    Activations Density 0.042%

    No Known Activations