© 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. 1-RES-MATRYOSHKA-DC
    7. 882
    Prev
    Next
    INDEX
    Explanations

    questions about the presence or necessity of specific information

    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
    weile
    -0.62
    TypedDataSet
    -0.61
    setVerticalGroup
    -0.60
     Dryden
    -0.57
     ingrat
    -0.56
     Jurí
    -0.56
     geste
    -0.56
     Tiro
    -0.56
     surla
    -0.56
     Perak
    -0.54
    POSITIVE LOGITS
     Is
    1.72
    Is
    1.68
    Does
    1.62
     Are
    1.60
     Does
    1.59
    Are
    1.58
    Has
    1.44
     Did
    1.44
    Did
    1.43
     Has
    1.41
    Activations Density 0.860%

    No Known Activations