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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 2673
    Prev
    Next
    INDEX
    Explanations

    the word "sure".

    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
    Guarantee
    -0.94
     guaranteeing
    -0.88
     guarantees
    -0.87
    RegistryLite
    -0.87
    guarantee
    -0.85
     ensuring
    -0.85
     Guarantee
    -0.82
     <=",
    -0.82
     guarante
    -0.81
     ensures
    -0.81
    POSITIVE LOGITS
     sure
    2.19
    sure
    1.92
     Sure
    1.79
    Sure
    1.76
     SURE
    1.68
     surely
    0.95
     certo
    0.82
     Surely
    0.80
     sûr
    0.77
    Surely
    0.76
    Activations Density 0.013%

    No Known Activations