© 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. 0-RES-MATRYOSHKA-DC
    7. 12620
    Prev
    Next
    INDEX
    Explanations

    references to inclusion or the presence of certain items or features within a broader context

    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
    kuje
    -0.53
     AssemblyTitle
    -0.52
     bulun
    -0.51
     населён
    -0.51
     whereas
    -0.50
     such
    -0.50
     simply
    -0.50
    timewa
    -0.49
     etc
    -0.49
    whereas
    -0.48
    POSITIVE LOGITS
    includes
    1.06
    Includes
    0.95
     includes
    0.90
     Includes
    0.88
     INCLUDES
    0.85
    CompleteListener
    0.65
     חיצוניים
    0.63
    +#+#
    0.61
    IntoConstraints
    0.60
    COUVER
    0.60
    Activations Density 0.008%

    No Known Activations