© 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. 3584
    Prev
    Next
    INDEX
    Explanations

    references to an unspecified or unknown degree of a certain concept or occurrence

    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
    MessageTagHelper
    -0.78
    UserScript
    -0.75
     lots
    -0.69
    omitempty
    -0.69
     Xunit
    -0.68
    Lots
    -0.66
     Nearly
    -0.66
    DllImport
    -0.65
     Lots
    -0.65
     Plenty
    -0.64
    POSITIVE LOGITS
     somehow
    2.28
     Somehow
    1.93
    Somehow
    1.90
     somewhat
    1.46
    somewhat
    1.38
     Somewhat
    1.24
    Somewhat
    1.23
     irgendwie
    1.02
     sometime
    0.87
     Somewhere
    0.86
    Activations Density 0.007%

    No Known Activations