© 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. 3525
    Prev
    Next
    INDEX
    Explanations

    legal language related to property rights and transactions

    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
    ThroughAttribute
    -0.77
    ResumeLayout
    -0.65
    脚注の使い方
    -0.60
    migrationBuilder
    -0.59
    CppMethod
    -0.59
    ГЛА
    -0.57
     переписи
    -0.57
    setViewportView
    -0.54
     intptr
    -0.53
     we
    -0.52
    POSITIVE LOGITS
    <bos>
    0.73
     themſelves
    0.64
     Cæsar
    0.64
     raiſ
    0.63
    SequentialGroup
    0.63
    ngdoc
    0.61
     Efq
    0.60
    soever
    0.60
     Majefty
    0.59
     Perſ
    0.59
    Activations Density 2.181%

    No Known Activations