© 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. 3-RES-MATRYOSHKA-DC
    7. 2740
    Prev
    Next
    INDEX
    Explanations

    the word 'stated', especially in legal contexts

    oai_token-act-pair · gemini-2.0-flash
    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
     commande
    -0.63
     mergeFrom
    -0.61
     AttributeSet
    -0.61
    <tbody>
    -0.58
     Peterson
    -0.57
    skraft
    -0.56
    Tazama
    -0.56
     val
    -0.54
    RegressionTest
    -0.54
    긴
    -0.54
    POSITIVE LOGITS
     stated
    2.20
    stated
    1.76
     stating
    1.31
     statements
    1.05
    statements
    1.05
     statement
    1.04
    statement
    1.01
     énon
    1.01
     Statements
    0.95
     declarado
    0.95
    Activations Density 0.019%

    No Known Activations