© 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. 2
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a key property or characteristic within a technical or mathematical context

    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
    Ứ
    -0.55
     epidemics
    -0.53
    tande
    -0.53
     dịch
    -0.53
    kolwiek
    -0.52
    stawa
    -0.52
     bày
    -0.51
     cuna
    -0.51
    EndInit
    -0.50
    념
    -0.50
    POSITIVE LOGITS
     property
    4.19
     Property
    3.73
    property
    3.70
     properties
    3.61
    Property
    3.59
     PROPERTY
    3.53
     Properties
    3.33
    properties
    3.11
    PROPERTY
    3.11
    Properties
    3.03
    Activations Density 1.913%

    No Known Activations