© 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. 930
    Prev
    Next
    INDEX
    Explanations

    references to policy evaluation and commentary, often emphasizing the importance or significance of the subject

    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
     onCancelled
    -0.63
    AsUp
    -0.62
    engertian
    -0.60
    idenav
    -0.59
     Jefus
    -0.59
    SharedDtor
    -0.57
     wysy
    -0.57
    UrlResolution
    -0.56
    tableFuture
    -0.56
    ########.
    -0.56
    POSITIVE LOGITS
     mark
    4.56
    mark
    4.19
     Mark
    3.98
    Mark
    3.97
     MARK
    3.95
     marks
    3.91
    MARK
    3.84
    marks
    3.63
     Marks
    3.42
     MARKS
    3.36
    Activations Density 0.308%

    No Known Activations