© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14874
    Prev
    Next
    INDEX
    Explanations

    numerical expressions indicating proportions or fractional parts

    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
     Roskov
    -0.62
    SharedCtor
    -0.61
    matchCondition
    -0.59
    :].
    -0.57
    weetie
    -0.56
    IUrlHelper
    -0.56
    woofer
    -0.54
    IsMutable
    -0.54
    RegistryLite
    -0.53
    lihood
    -0.52
    POSITIVE LOGITS
    Vanjske
    0.63
    xito
    0.58
     maschile
    0.58
     IBOutlet
    0.57
     للاسماء
    0.57
     angolo
    0.56
    AndEndTag
    0.56
     Aplica
    0.56
     picioare
    0.56
     Turquie
    0.54
    Activations Density 0.108%

    No Known Activations