© 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. 1982
    Prev
    Next
    INDEX
    Explanations

    the word "really"

    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
     passés
    -0.80
     serupa
    -0.79
     épar
    -0.79
     pertanto
    -0.78
    arvi
    -0.77
     inoltre
    -0.77
     Kowal
    -0.75
     NOC
    -0.75
    ValueStyle
    -0.75
    ormais
    -0.74
    POSITIVE LOGITS
     really
    3.05
    really
    2.80
     Really
    2.70
    Really
    2.67
     REALLY
    2.39
     realy
    2.17
     realmente
    1.91
     vraiment
    1.83
     wirklich
    1.69
     truly
    1.61
    Activations Density 0.167%

    No Known Activations