© 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. 2-RES-MATRYOSHKA-DC
    7. 5952
    Prev
    Next
    INDEX
    Explanations

    references to network configurations and technical standards

    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
     Brom
    -0.64
     Pes
    -0.63
     انف
    -0.62
     Krim
    -0.60
     mun
    -0.59
    pédie
    -0.59
    ïn
    -0.57
     Warburton
    -0.57
     Lal
    -0.56
     Xe
    -0.56
    POSITIVE LOGITS
    NC
    2.83
     NC
    2.61
    nc
    2.11
     nc
    1.91
     Carolina
    1.76
    Carolina
    1.72
     CAROLINA
    1.41
     Nc
    1.40
     carolina
    1.39
    carolina
    1.30
    Activations Density 0.013%

    No Known Activations