© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    references to statistical concepts, particularly Markov kernels, densities, and experiments

    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
     chrétien
    -0.59
     giuri
    -0.51
    complexContent
    -0.50
     plonge
    -0.49
     equipada
    -0.49
    orique
    -0.48
     baños
    -0.48
     endowed
    -0.48
     judiciales
    -0.47
     stationnement
    -0.47
    POSITIVE LOGITS
    UrlResolution
    0.80
    BeginContext
    0.78
    Unmarshaller
    0.74
     createSprite
    0.73
    bibinfo
    0.71
     Wikimedijinoj
    0.71
     useRouter
    0.68
    AccessFile
    0.68
    BibitemShut
    0.68
    Geplaatst
    0.67
    Activations Density 1.911%

    No Known Activations