© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13640
    Prev
    Next
    INDEX
    Explanations

    references to the generality or universality of a concept or approach

    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
    Reception
    -0.65
    reception
    -0.62
    >`
    -0.60
     lenker
    -0.59
     reception
    -0.57
     Macromolecules
    -0.57
     Attendance
    -0.55
    ftagPool
    -0.55
     attendance
    -0.54
     Reception
    -0.54
    POSITIVE LOGITS
     generality
    2.27
    :`
    1.44
     المعيارى
    0.70
    Britannique
    0.64
    tonode
    0.59
     CRF
    0.57
     AssemblyTitle
    0.56
     Anſ
    0.56
    mallows
    0.54
    ześnie
    0.54
    Activations Density 0.003%

    No Known Activations