© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 577
    Prev
    Next
    INDEX
    Explanations

    the word "note" followed by "that"

    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
    Portale
    -0.85
     незавершена
    -0.78
    saraba
    -0.77
     Administrativna
    -0.61
     Eup
    -0.60
    IUrlHelper
    -0.60
    Sov
    -0.59
    AsUp
    -0.59
    Déf
    -0.59
    Cuánt
    -0.59
    POSITIVE LOGITS
     note
    3.31
     Note
    3.22
    Note
    2.91
    note
    2.84
     NOTE
    2.84
     notes
    2.53
     Notes
    2.47
    NOTE
    2.44
    Notes
    2.31
    notes
    2.22
    Activations Density 0.289%

    No Known Activations