© 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. 12717
    Prev
    Next
    INDEX
    Explanations

    references or annotations related to specific genes, proteins, or molecular assays

    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
    Autoritní
    -0.67
    RegressionTest
    -0.66
    QMetaType
    -0.61
     ModelExpression
    -0.61
    ็จ
    -0.59
    quem
    -0.55
    msgTypes
    -0.54
    CloseOperation
    -0.53
     vun
    -0.53
    tagHelperRunner
    -0.52
    POSITIVE LOGITS
     FIT
    2.70
    FIT
    2.41
     Fit
    0.83
    Fit
    0.82
     appunt
    0.66
     magasiner
    0.59
     blessés
    0.59
     */;
    0.58
     vaut
    0.57
     lezioni
    0.57
    Activations Density 0.002%

    No Known Activations