© 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. 8
    Prev
    Next
    INDEX
    Explanations

    references to experiments and models involving the Bell inequality and their associated characteristics

    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
     hunne
    -0.92
     spalle
    -0.91
     figliu
    -0.82
     eterno
    -0.82
     ardından
    -0.82
     prossima
    -0.79
     acquittal
    -0.79
     nicio
    -0.77
     déchir
    -0.76
     abbandon
    -0.75
    POSITIVE LOGITS
     model
    1.89
     structure
    1.43
     mode
    1.41
     Model
    1.41
     form
    1.33
    model
    1.30
     type
    1.27
     element
    1.27
     models
    1.25
     pattern
    1.25
    Activations Density 18.533%

    No Known Activations