© 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. 13413
    Prev
    Next
    INDEX
    Explanations

    the presence and characteristics of starch granules in samples

    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
    abestanden
    -0.68
    phosa
    -0.66
    Hauptartikel
    -0.64
    syms
    -0.61
    énario
    -0.60
    تقاوى
    -0.60
     propOrder
    -0.60
    ámb
    -0.59
    bisoft
    -0.59
    Palindrome
    -0.59
    POSITIVE LOGITS
     granules
    3.23
     granule
    3.08
     granular
    1.50
     granulated
    1.00
     intptr
    0.71
    Gran
    0.65
     Gran
    0.64
     powder
    0.62
     cucchiaio
    0.61
    gran
    0.60
    Activations Density 0.003%

    No Known Activations