© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 644
    Prev
    Next
    INDEX
    Explanations

    speech attribution tags like "says", "replied", or "explained"

    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
    uesia
    -0.54
    ImageContext
    -0.51
    StructEnd
    -0.50
     bukti
    -0.46
    edos
    -0.46
    SequentialGroup
    -0.44
     estekak
    -0.44
    ️
    -0.44
    IVEREF
    -0.44
    Rohy
    -0.43
    POSITIVE LOGITS
    وأضاف
    0.73
     >=",
    0.73
    Says
    0.72
    وقال
    0.70
    JNIEnv
    0.70
    Slf
    0.67
    stdafx
    0.64
     Says
    0.64
    Según
    0.63
    says
    0.62
    Activations Density 0.124%

    No Known Activations