© 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. 26
    Prev
    Next
    INDEX
    Explanations

    references to specific online channels or media sources

    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
     propOrder
    -1.14
    setVerticalGroup
    -1.06
     kaarangay
    -1.05
    EndGlobalSection
    -0.93
    PerformLayout
    -0.91
     дописавши
    -0.91
    IUrlHelper
    -0.89
     Савезне
    -0.88
    ----</
    -0.87
     विश्वसनीयता
    -0.82
    POSITIVE LOGITS
    ç
    0.60
    di
    0.53
    ,
    0.50
    fe
    0.49
    ta
    0.46
    ls
    0.46
    ry
    0.45
     {},
    0.45
    er
    0.44
    es
    0.44
    Activations Density 5.905%

    No Known Activations