© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12963
    Prev
    Next
    INDEX
    Explanations

    the neural network's focus on measuring the degree of convective mixing in stellar models

    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
    Mixed
    -1.23
     Mixed
    -1.19
     mixed
    -1.16
    mixed
    -1.14
     mixt
    -0.84
     mixte
    -0.84
    WebVitals
    -0.83
    IVEREF
    -0.81
     gemis
    -0.80
    IsContent
    -0.80
    POSITIVE LOGITS
     mixing
    1.98
     Mixing
    1.80
    Mixing
    1.59
    mixing
    1.56
     mixer
    0.63
    таратура
    0.62
     combining
    0.56
     الحره
    0.54
     mixers
    0.54
     concor
    0.53
    Activations Density 0.002%

    No Known Activations