© 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. 3-RES-MATRYOSHKA-DC
    7. 3038
    Prev
    Next
    INDEX
    Explanations

    the word 'state' or 'states' often in a physics context

    oai_token-act-pair · gemini-2.0-flash
    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
     Provincial
    -0.67
    rouvez
    -0.65
     country
    -0.65
     province
    -0.57
    namentales
    -0.57
     County
    -0.54
    Government
    -0.53
    Provincial
    -0.53
     provincial
    -0.53
    actéristique
    -0.53
    POSITIVE LOGITS
    abetes
    0.82
    SharedDtor
    0.82
    rmtree
    0.67
    cshtml
    0.66
     setae
    0.65
    UnusedPrivate
    0.64
     transfieras
    0.63
     nakalista
    0.61
     dysplasia
    0.61
    WIRE
    0.60
    Activations Density 0.083%

    No Known Activations