© 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. 1-RES-MATRYOSHKA-DC
    7. 202
    Prev
    Next
    INDEX
    Explanations

    references to measurements of total energy or total quantities

    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
    pensive
    -0.70
     Waray
    -0.64
    varargin
    -0.60
     navideños
    -0.58
    besondere
    -0.57
    melada
    -0.56
    RetentionPolicy
    -0.56
     influential
    -0.54
     skär
    -0.54
     <>",
    -0.54
    POSITIVE LOGITS
     total
    4.56
    total
    4.03
    Total
    3.97
     Total
    3.95
     TOTAL
    3.63
     totale
    3.48
    TOTAL
    3.41
     totales
    3.02
     totaal
    2.80
    getTotal
    2.61
    Activations Density 0.639%

    No Known Activations