© 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. 2934
    Prev
    Next
    INDEX
    Explanations

    references to nuclear-related phenomena, properties, or mechanisms

    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
     nuclei
    -1.23
     nucleus
    -1.20
     Nucleus
    -1.07
    Nucle
    -0.99
     propOrder
    -0.96
    nucleus
    -0.94
     noyau
    -0.82
     AssemblyCulture
    -0.75
    GeoNames
    -0.74
    новништво
    -0.71
    POSITIVE LOGITS
     nuclear
    2.22
     Nuclear
    1.89
    nuclear
    1.83
    Nuclear
    1.77
     NUCLEAR
    1.65
     nucléaire
    1.23
    uclear
    1.01
     ядер
    1.01
     nukes
    0.94
     nuke
    0.76
    Activations Density 0.006%

    No Known Activations