© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    the word "would" followed by auxiliary verbs or verbs of thinking

    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
    can
    -0.83
     can
    -0.81
     puoi
    -0.81
    Cain
    -0.79
     Adair
    -0.73
     possiamo
    -0.73
     puedes
    -0.72
    busch
    -0.72
     Schrader
    -0.71
     Maguire
    -0.71
    POSITIVE LOGITS
     would
    2.25
     Would
    2.11
    Would
    2.11
    would
    2.09
     WOULD
    2.00
     wäre
    1.38
     wären
    1.38
    Wouldn
    1.24
     seraient
    1.24
     Wouldn
    1.20
    Activations Density 0.858%

    No Known Activations