© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    references to optical lenses, particularly super-wide-angle lenses

    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
     aza
    -0.62
     Giovan
    -0.59
    ymmetry
    -0.57
    Flaming
    -0.57
     Shearer
    -0.57
    WindowConstants
    -0.56
     syl
    -0.55
     flam
    -0.55
     simplifié
    -0.54
     Burnham
    -0.54
    POSITIVE LOGITS
     lens
    3.16
     lenses
    2.77
     Lens
    2.73
    Lens
    2.47
    lens
    2.41
     Lenses
    2.41
    レンズ
    1.62
     lentes
    1.38
     lente
    1.29
     レンズ
    1.29
    Activations Density 0.010%

    No Known Activations