© 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. 2-RES-MATRYOSHKA-DC
    7. 5899
    Prev
    Next
    INDEX
    Explanations

    references to different varieties or types of objects

    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
     للمعارف
    -1.05
    various
    -0.71
     Runtime
    -0.68
     مشين
    -0.67
     various
    -0.67
    contentValues
    -0.65
     variants
    -0.62
    Various
    -0.61
     ***!
    -0.61
     variations
    -0.60
    POSITIVE LOGITS
     variety
    2.16
    variety
    2.03
     Variety
    1.78
    Variety
    1.69
     variedad
    1.51
     variedade
    1.44
     varietà
    1.44
     varieties
    1.42
     variété
    1.36
     Varieties
    1.29
    Activations Density 0.010%

    No Known Activations