© 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. 2-RES-MATRYOSHKA-DC
    7. 5752
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ghel" or "Ghem"

    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
    ,+
    -0.54
     Geller
    -0.52
    axel
    -0.52
    rambled
    -0.52
    letar
    -0.50
    зулта
    -0.49
     Pel
    -0.47
    flink
    -0.46
    imenta
    -0.46
    Dav
    -0.46
    POSITIVE LOGITS
    gh
    4.16
    ghs
    2.58
    GH
    2.55
     gh
    2.38
    Gh
    2.00
    ghh
    1.98
    AGH
    1.91
     GH
    1.90
    ghu
    1.84
     Gh
    1.79
    Activations Density 0.012%

    No Known Activations