© 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. 3628
    Prev
    Next
    INDEX
    Explanations

    subjective or evaluative language, such as opinions, judgments, or expressions of belief

    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
    strokeStyle
    -0.52
    MouseAdapter
    -0.50
     However
    -0.50
    하지
    -0.49
    However
    -0.48
    harusnya
    -0.48
     But
    -0.46
    Yet
    -0.46
    roppo
    -0.46
    ano
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.94
     متعلقه
    0.89
     الحره
    0.73
     Wicidata
    0.72
    adaptiveStyles
    0.72
     <<<<<<<<<<<<<<
    0.69
    makeConstraints
    0.69
    fromCharCode
    0.68
    Diweddarwch
    0.66
    itattu
    0.66
    Activations Density 0.153%

    No Known Activations