© 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. 2-RES-MATRYOSHKA-DC
    7. 5583
    Prev
    Next
    INDEX
    Explanations

    references to interesting or notable intermediate results or states

    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
    tagHelperRunner
    -0.87
    MEAN
    -0.76
    MessageTagHelper
    -0.73
     Mean
    -0.72
     Wikimedijinoj
    -0.68
     cucchiai
    -0.68
     Италијани
    -0.68
     Lyra
    -0.66
    PAN
    -0.66
    Искәрмәләр
    -0.65
    POSITIVE LOGITS
     intermediate
    3.38
    intermediate
    3.19
    Intermediate
    3.06
     Intermediate
    3.02
     intermediates
    2.33
     intermédiaire
    2.00
     intermedio
    1.86
     intermediary
    1.82
     intermedi
    1.71
    MEDIATE
    1.63
    Activations Density 0.011%

    No Known Activations