© 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. 48
    Prev
    Next
    INDEX
    Explanations

    relative pronouns such as "that" and "which".

    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
    r
    -0.71
     Olms
    -0.57
     trefoil
    -0.57
    ag
    -0.57
    fone
    -0.57
    R
    -0.56
     appraisals
    -0.56
    cy
    -0.55
     rowing
    -0.55
     laterales
    -0.54
    POSITIVE LOGITS
     which
    1.65
     Which
    1.55
     WHICH
    1.54
    which
    1.46
     wich
    1.45
    Which
    1.45
     who
    1.32
     które
    1.23
     οποίο
    1.19
    ซึ่ง
    1.17
    Activations Density 2.499%

    No Known Activations