© 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. 3028
    Prev
    Next
    INDEX
    Explanations

    the definition of a specific physical constant or parameter

    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
    define
    -1.19
    def
    -0.98
     Def
    -0.85
    Def
    -0.83
     def
    -0.74
     DEF
    -0.73
    defn
    -0.71
     acheté
    -0.69
    DEF
    -0.66
     defence
    -0.65
    POSITIVE LOGITS
     defined
    1.41
    defined
    1.21
     Defined
    1.05
    Defined
    1.02
     definido
    0.68
     definida
    0.66
     חיצוניים
    0.63
     specified
    0.62
    )";
    0.60
     delineated
    0.60
    Activations Density 0.017%

    No Known Activations