© 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. 565
    Prev
    Next
    INDEX
    Explanations

    inquiries about methods or processes

    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
     when
    -0.79
     When
    -0.78
    When
    -0.78
    when
    -0.78
    Cuando
    -0.76
     cuando
    -0.74
     quando
    -0.73
    cuando
    -0.73
     όταν
    -0.72
     lorsque
    -0.72
    POSITIVE LOGITS
     how
    4.09
    how
    3.23
     How
    2.94
    How
    2.88
     HOW
    2.86
    HOW
    2.75
     cómo
    2.17
     hvordan
    1.97
    如何
    1.91
    howto
    1.88
    Activations Density 0.054%

    No Known Activations