© 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. 4761
    Prev
    Next
    INDEX
    Explanations

    references to specific descriptive terms or phrases indicating detailed explanations or definitions

    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
     XNUMX
    -0.84
     Jefus
    -0.83
    styleType
    -0.79
     Efq
    -0.78
    PreferredItem
    -0.78
     himſelf
    -0.77
     Theſe
    -0.77
     Majefty
    -0.75
     whoſe
    -0.74
    TagHelper
    -0.73
    POSITIVE LOGITS
     whilst
    0.76
     Whilst
    0.73
     läßt
    0.71
     muß
    0.66
    Whilst
    0.66
     daß
    0.64
    faßt
    0.63
     şi
    0.57
     that
    0.56
     bahawa
    0.56
    Activations Density 0.065%

    No Known Activations