© 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. 4459
    Prev
    Next
    INDEX
    Explanations

    references to the necessity or requirement of specific techniques, methods, or studies

    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
     require
    -0.99
    require
    -0.92
     REQUIRE
    -0.92
     Require
    -0.89
     requirement
    -0.87
     Requirement
    -0.86
    requirement
    -0.85
     Requirements
    -0.83
    requirements
    -0.82
     REQUIREMENTS
    -0.81
    POSITIVE LOGITS
     needed
    2.11
     Needed
    2.03
    needed
    1.92
    Needed
    1.83
     NEEDED
    1.75
     wanted
    1.51
    wanted
    1.39
     Wanted
    1.33
     desired
    1.32
    Wanted
    1.30
    Activations Density 0.081%

    No Known Activations