© 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. 8-RES-MATRYOSHKA-DC
    4. 29738
    Prev
    Next
    INDEX
    Explanations

    conjunctions, prepositions, and other words that connect clauses, and indicate logical relationships

    oai_token-act-pair · gemini-2.0-flash
    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
    脚注の使い方
    -0.67
    MessageOf
    -0.63
     harbors
    -0.55
     MERCHANTABILITY
    -0.54
    fren
    -0.54
    ględ
    -0.54
    TestingModule
    -0.53
    GeoNames
    -0.52
     않습니다
    -0.52
    μφωνα
    -0.52
    POSITIVE LOGITS
    DidLoad
    0.60
    windowFixed
    0.56
     będę
    0.52
     lumea
    0.52
     stră
    0.52
    enangan
    0.51
    便
    0.50
     bcrypt
    0.49
    '):
    
    0.49
    orkin
    0.49
    Activations Density 0.057%

    No Known Activations