© 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. 5911
    Prev
    Next
    INDEX
    Explanations

    expressions of strong disagreement or emphasis

    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
     well
    -0.99
     även
    -0.75
    well
    -0.72
     also
    -0.70
    WELL
    -0.69
    Well
    -0.66
     WELL
    -0.66
     suficiente
    -0.65
     aswell
    -0.65
    enumi
    -0.65
    POSITIVE LOGITS
     Too
    1.18
    Too
    1.16
    too
    1.13
     too
    1.12
     TOO
    0.91
    TOO
    0.90
    出版年
    0.82
    DockStyle
    0.81
     слишком
    0.74
     troppo
    0.69
    Activations Density 0.032%

    No Known Activations