© 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. 4837
    Prev
    Next
    INDEX
    Explanations

    references to assertions or claims of rights

    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
     GenerationType
    -0.88
    はじめに
    -0.68
    ArgumentParser
    -0.68
    +#+#
    -0.67
    kenes
    -0.63
    EndContext
    -0.62
    واره
    -0.61
    TagMode
    -0.61
    uxxxx
    -0.61
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
     asserted
    1.50
     asserts
    1.39
     asserting
    1.38
     assertion
    1.26
     Assertion
    1.09
     assert
    1.06
     assertions
    1.06
    asser
    0.96
    assertion
    0.96
     assertive
    0.87
    Activations Density 0.020%

    No Known Activations