© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14441
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical or structural sets, such as construction or toy building kits

    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
    TemporalType
    -0.77
     Audiodateien
    -0.74
    amaño
    -0.71
     '\\;'
    -0.68
    __*/
    -0.66
    aarrggbb
    -0.61
    hamcrest
    -0.61
     onCreateView
    -0.57
     springfox
    -0.57
    Diweddarwch
    -0.57
    POSITIVE LOGITS
     Gilbert
    3.77
    Gilbert
    3.56
     GILBERT
    2.55
    GIL
    1.05
     gil
    1.03
    gil
    0.85
     Gil
    0.80
    Gil
    0.73
     GIL
    0.65
     Gilberto
    0.62
    Activations Density 0.000%

    No Known Activations