© 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. 4227
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emphasis or certainty

    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
     real
    -0.72
    quasi
    -0.70
     quas
    -0.69
     quasi
    -0.67
     Quasi
    -0.66
     걸
    -0.66
     Quis
    -0.66
    =$((
    -0.66
    real
    -0.65
    reggio
    -0.65
    POSITIVE LOGITS
     quite
    2.38
    quite
    2.23
     Quite
    2.20
    Quite
    2.13
     uite
    1.30
     ganske
    0.96
     bastante
    0.86
     khá
    0.77
    databind
    0.74
     actually
    0.73
    Activations Density 0.008%

    No Known Activations