© 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. 68
    Prev
    Next
    INDEX
    Explanations

    double negatives

    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
    сього
    -0.63
     quoque
    -0.60
     respectivement
    -0.59
     postup
    -0.57
     eventualmente
    -0.57
     tambi
    -0.56
    along
    -0.55
     sometime
    -0.54
     seleccionadas
    -0.54
     gjerne
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    1.12
     Not
    1.06
    (!__
    1.05
     nor
    1.02
    AddTagHelper
    1.02
     neither
    1.00
    RTDA
    0.99
     No
    0.99
     nenhuma
    0.97
     otomatig
    0.95
    Activations Density 5.834%

    No Known Activations