© 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. 1063
    Prev
    Next
    INDEX
    Explanations

    references to the concept of viewing or visualizing content

    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
     Review
    -1.36
     review
    -1.33
     Reviews
    -1.32
    Review
    -1.31
     Rev
    -1.30
     reviews
    -1.28
    Rev
    -1.25
     REVIEW
    -1.24
    review
    -1.21
     reviewed
    -1.19
    POSITIVE LOGITS
     view
    3.88
    view
    3.42
     View
    3.41
     VIEW
    3.20
    View
    3.09
     views
    2.89
    VIEW
    2.88
     Views
    2.55
    views
    2.39
     VIEWS
    2.33
    Activations Density 0.097%

    No Known Activations