© 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. 3169
    Prev
    Next
    INDEX
    Explanations

    questions about database constraints and key properties

    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
     She
    -0.46
    וך
    -0.45
     négo
    -0.43
     nyug
    -0.43
     kérd
    -0.41
     picado
    -0.41
     személy
    -0.40
    splitlines
    -0.40
    jning
    -0.40
    Erreferentziak
    -0.40
    POSITIVE LOGITS
    HasForeignKey
    0.98
     للمعارف
    0.81
    AlterField
    0.78
    WriteBarrier
    0.78
    CrossRef
    0.77
     onCancelled
    0.75
    ⓧ
    0.75
    mappedBy
    0.73
     betweenstory
    0.68
    RectangleBorder
    0.68
    Activations Density 0.488%

    No Known Activations