© 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. 11012
    Prev
    Next
    INDEX
    Explanations

    references to technical and industrial terms related to machinery, components, or engineering systems

    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
     виправивши
    -0.81
    principalTable
    -0.73
    GEBURTSDATUM
    -0.67
    Rüyada
    -0.62
    MessageTagHelper
    -0.61
     Roskov
    -0.61
    msgTypes
    -0.60
     betweenstory
    -0.60
    parsedMessage
    -0.60
    PostInfinity
    -0.58
    POSITIVE LOGITS
    Axis
    1.37
    ames
    1.09
    Beat
    0.81
    AMES
    0.76
    AXIS
    0.74
     Beat
    0.73
    RAI
    0.73
     Axis
    0.67
     Dickinson
    0.65
    LOOP
    0.62
    Activations Density 0.020%

    No Known Activations