© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    features related to specific molecular or chemical properties, particularly the presence of particular enzyme variants or analogs

    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
     Normdatei
    -0.54
     Savoy
    -0.50
    ABCD
    -0.48
    kiel
    -0.44
    MMV
    -0.44
     undercut
    -0.44
     Alpha
    -0.43
    aimerais
    -0.43
    BagConstraints
    -0.43
    kho
    -0.42
    POSITIVE LOGITS
     insignificant
    1.33
     insign
    1.15
     Solicitor
    0.97
     >=",
    0.94
    haha
    0.92
    otri
    0.89
     solicitor
    0.88
     unimportant
    0.78
    HasForeignKey
    0.77
    IndentedString
    0.77
    Activations Density 0.006%

    No Known Activations