© 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. 6-RES-MATRYOSHKA-DC
    7. 757
    Prev
    Next
    INDEX
    Explanations

    phrases using the word "compared"

    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
    khana
    -0.71
    Hauptartikel
    -0.67
     PLL
    -0.66
     Arty
    -0.62
     trajets
    -0.60
     flott
    -0.60
    ثيق
    -0.60
    disciplinary
    -0.59
    PLL
    -0.59
     tacit
    -0.59
    POSITIVE LOGITS
     compared
    1.91
     comparison
    1.63
    compared
    1.63
     Compared
    1.63
     compare
    1.60
    Compared
    1.55
     dibandingkan
    1.49
    compare
    1.47
     Compare
    1.46
    Compare
    1.45
    Activations Density 0.447%

    No Known Activations