© 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. 292
    Prev
    Next
    INDEX
    Explanations

    the word "non" and phrases containing "non-"

    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
    ("~/
    -0.76
    DockStyle
    -0.72
     accro
    -0.70
     rése
    -0.69
     vectorielle
    -0.68
     Apprentices
    -0.68
     Idy
    -0.68
    δου
    -0.68
    Encyclo
    -0.67
    myModal
    -0.67
    POSITIVE LOGITS
     non
    1.80
    Non
    1.73
    non
    1.73
     Non
    1.68
     NON
    1.65
    NON
    1.56
    非
    1.39
     nons
    1.16
     nong
    1.13
     非
    1.13
    Activations Density 0.450%

    No Known Activations