© 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. 3-RES-MATRYOSHKA-DC
    7. 143
    Prev
    Next
    INDEX
    Explanations

    the word "which" and sometimes related 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
    éens
    -0.70
     autocollant
    -0.70
     ganze
    -0.63
    Reentrant
    -0.63
     Baton
    -0.62
     olsa
    -0.60
    fone
    -0.60
     Katal
    -0.60
    PEN
    -0.60
     Folsom
    -0.60
    POSITIVE LOGITS
     which
    2.28
     WHICH
    2.14
    which
    2.13
     Which
    2.08
    Which
    1.98
     wich
    1.52
    hich
    1.49
     welches
    1.34
     والتي
    1.34
    ซึ่ง
    1.33
    Activations Density 1.147%

    No Known Activations