© 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. 0-RES-MATRYOSHKA-DC
    7. 11674
    Prev
    Next
    INDEX
    Explanations

    references to median values or median-related data

    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
     deleteUser
    -0.58
    Билгалдахарш
    -0.54
    GenerationType
    -0.53
    στα
    -0.50
     postData
    -0.50
     Junto
    -0.50
     scales
    -0.49
    ProcessEvent
    -0.49
     guts
    -0.48
    ControllerAdvice
    -0.47
    POSITIVE LOGITS
    Median
    1.19
    median
    0.96
    RCA
    0.92
    ThreadPool
    0.90
    θη
    0.86
     Préférences
    0.74
    clus
    0.72
    illus
    0.72
    enton
    0.72
    omaterials
    0.72
    Activations Density 0.025%

    No Known Activations