© 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
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2527
    Prev
    Next
    INDEX
    Explanations

    the word "emphasis" or "emphasizing"

    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
    ISupport
    -0.55
     fruition
    -0.54
    зер
    -0.53
    いざ
    -0.53
     destiny
    -0.52
     deten
    -0.51
    toHaveBeenCalled
    -0.51
     Neto
    -0.50
     kons
    -0.49
     coul
    -0.49
    POSITIVE LOGITS
     emphasize
    2.02
    emphasis
    1.98
     emphasis
    1.96
     emphasized
    1.91
     Emphasis
    1.91
     emphasizing
    1.90
     emphasise
    1.90
     emphasizes
    1.89
     emphas
    1.83
    Emphasis
    1.79
    Activations Density 0.088%

    No Known Activations