© 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. 11348
    Prev
    Next
    INDEX
    Explanations

    measurements related to statistical robustness

    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
    MigrationBuilder
    -0.58
    NameInMap
    -0.56
    __*/
    -0.56
     StatefulWidget
    -0.55
    :]:
    -0.54
    ább
    -0.52
    อิ
    -0.51
     le
    -0.50
    !*\
    -0.50
     access
    -0.48
    POSITIVE LOGITS
     Grim
    1.14
    Grim
    1.12
     robustness
    1.10
     standpoint
    1.07
     slam
    0.98
     Shotgun
    0.97
    vall
    0.96
    slam
    0.93
     shotgun
    0.90
     AssemblyTitle
    0.83
    Activations Density 0.006%

    No Known Activations