© 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. 5874
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of organized social or political grouping, specifically "party."

    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
    calli
    -0.49
     staged
    -0.43
    XmlAccessType
    -0.43
     next
    -0.43
     prácti
    -0.43
    mmas
    -0.43
    escent
    -0.42
     onts
    -0.42
    ウンテン
    -0.42
     kesk
    -0.41
    POSITIVE LOGITS
    party
    1.03
    ########.
    0.86
    Party
    0.79
     GenerationType
    0.79
    ]")]
    0.77
     StatelessWidget
    0.75
    PARTY
    0.75
     intptr
    0.74
    ">//
    0.73
    ագրություններ
    0.72
    Activations Density 0.006%

    No Known Activations