© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15213
    Prev
    Next
    INDEX
    Explanations

    references to genetic and molecular biology techniques or substances

    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
    Parameterized
    -0.58
     Accordingly
    -0.56
    hadores
    -0.56
     propOrder
    -0.56
    asca
    -0.52
     Deber
    -0.52
     Uts
    -0.50
     phan
    -0.49
     вікі
    -0.49
    ługo
    -0.49
    POSITIVE LOGITS
    lei
    3.80
    LEI
    1.77
    Lei
    1.37
     lei
    1.35
     Lei
    1.25
    leo
    1.03
    alei
    0.82
    mei
    0.77
    CloseOperation
    0.76
    leih
    0.75
    Activations Density 0.002%

    No Known Activations