© 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. 0-RES-MATRYOSHKA-DC
    7. 11726
    Prev
    Next
    INDEX
    Explanations

    uses the word "Yo" as an identifier or signal, indicating it is looking for or activates in relation to the term "Yo"

    oai_token-act-pair · gpt-4.1-nano
    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
    prefixer
    -0.72
    <?
    -0.59
     gug
    -0.57
    medriver
    -0.57
    NRAS
    -0.53
    ólicas
    -0.52
     stř
    -0.50
     Grundstück
    -0.50
     Ritz
    -0.49
    ----+
    -0.49
    POSITIVE LOGITS
     Yo
    2.92
     yo
    2.58
    Yo
    2.48
     YO
    1.98
     yoghurt
    1.02
     yoy
    0.95
     Yojana
    0.86
     Yok
    0.83
     yogurt
    0.75
     yoke
    0.74
    Activations Density 0.001%

    No Known Activations