© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    the word "parties" in legal documents

    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
     PARTY
    -1.13
     Party
    -1.13
     party
    -1.08
    Party
    -1.04
    party
    -0.99
     partij
    -0.92
     Partei
    -0.88
    PARTY
    -0.86
    bootstrapcdn
    -0.70
    __*/
    -0.68
    POSITIVE LOGITS
     parties
    0.76
     teams
    0.56
    uxta
    0.53
    ölker
    0.49
    Clik
    0.49
    EnableWeb
    0.48
     Teams
    0.48
    Teams
    0.48
    AndroidJUnit
    0.47
    Parties
    0.47
    Activations Density 0.004%

    No Known Activations