© 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. 3179
    Prev
    Next
    INDEX
    Explanations

    references to prior art or existing techniques

    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
     Italijanski
    -0.55
     artist
    -0.54
     Himo
    -0.53
     artistic
    -0.51
     Künstler
    -0.50
     ανά
    -0.50
     Artist
    -0.48
     Walkover
    -0.47
     ARTISTS
    -0.47
     sanat
    -0.47
    POSITIVE LOGITS
    expandindo
    0.75
    CppMethod
    0.73
    __*/
    0.73
     Efq
    0.70
    troppo
    0.68
     pitié
    0.66
    ंदीखरीदारी
    0.65
     consultato
    0.65
     prioritise
    0.64
    StoryboardSegue
    0.63
    Activations Density 0.007%

    No Known Activations