© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    mentions of measurements, calculations, or estimations, especially related to scientific data

    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
    ########.
    -0.67
     censiti
    -0.65
    цездатний
    -0.64
     doGet
    -0.63
    
    -0.63
    npos
    -0.63
    Autoritní
    -0.61
    QObject
    -0.61
     nakalista
    -0.61
    xture
    -0.60
    POSITIVE LOGITS
     calculated
    1.77
    calculated
    1.41
     Calculated
    1.35
     computed
    1.23
    Calculated
    1.17
     determined
    0.99
    computed
    0.96
     measured
    0.91
    determined
    0.83
     Determined
    0.81
    Activations Density 0.056%

    No Known Activations