© 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. 1462
    Prev
    Next
    INDEX
    Explanations

    the word 'that', especially preceding a clause

    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
     who
    -1.24
     which
    -1.04
     whom
    -1.02
    who
    -1.00
     WHICH
    -0.99
     Which
    -0.95
     Who
    -0.90
     Whom
    -0.90
    which
    -0.89
    whom
    -0.89
    POSITIVE LOGITS
    ởi
    0.57
     irrevocable
    0.56
    INITY
    0.52
    Portale
    0.51
     Ample
    0.50
     gebo
    0.50
     loisirs
    0.49
     hôn
    0.49
     totalidad
    0.49
     kelapa
    0.49
    Activations Density 0.570%

    No Known Activations