© 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. 896
    Prev
    Next
    INDEX
    Explanations

    the word "since" and sometimes other nearby words

    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
     Leah
    -0.81
     Waray
    -0.68
     Bew
    -0.67
    iência
    -0.66
    hecta
    -0.64
    Leah
    -0.63
    abestanden
    -0.63
     Rebekah
    -0.63
    bigniew
    -0.62
     Pires
    -0.62
    POSITIVE LOGITS
    since
    1.64
     since
    1.57
     SINCE
    1.56
     Since
    1.38
    Since
    1.35
     fince
    1.31
     Depuis
    1.12
    depuis
    1.01
    Seit
    0.98
    Depuis
    0.94
    Activations Density 0.215%

    No Known Activations