© 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. 13466
    Prev
    Next
    INDEX
    Explanations

    the activation of system-related phrases indicating operational success

    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
     Relations
    -1.42
     RELATIONS
    -1.29
     relations
    -1.19
    Relations
    -1.17
    relations
    -1.05
     Affairs
    -1.03
    operating
    -0.97
     saites
    -0.95
     CanadaChoose
    -0.94
    EDEFAULT
    -0.91
    POSITIVE LOGITS
     operations
    1.08
     Operations
    0.83
    operations
    0.78
     OPERATIONS
    0.76
    Operations
    0.65
     processes
    0.61
     operações
    0.61
     process
    0.60
     processos
    0.58
     opérations
    0.57
    Activations Density 0.005%

    No Known Activations