© 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. 441
    Prev
    Next
    INDEX
    Explanations

    references to highly emphasized or extreme quantities or intensities

    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
    awtextra
    -0.94
     autant
    -0.81
     soudain
    -0.79
     houſe
    -0.72
     giusti
    -0.70
     setidaknya
    -0.70
    льше
    -0.70
     ſche
    -0.70
    elesaian
    -0.69
     helst
    -0.68
    POSITIVE LOGITS
     very
    4.38
    very
    3.86
    Very
    3.84
     Very
    3.72
     VERY
    3.34
    VERY
    3.30
     muy
    2.91
     très
    2.89
     sehr
    2.66
     extremely
    2.38
    Activations Density 1.328%

    No Known Activations