© 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. 6880
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies, data, or concepts related to molecular mechanisms

    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
    molecules
    -1.55
     molecules
    -1.45
     molecule
    -1.34
     Molecules
    -1.30
     atoms
    -1.22
     Molecule
    -1.19
    molecule
    -1.15
    atoms
    -1.05
     moléculas
    -1.00
     atom
    -0.97
    POSITIVE LOGITS
     molecular
    1.56
     Molecular
    1.40
    Molecular
    1.34
    molecular
    1.07
    enskap
    0.56
    itest
    0.52
    kite
    0.49
    text
    0.49
    test
    0.49
     sot
    0.49
    Activations Density 0.010%

    No Known Activations