© 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. 3-RES-MATRYOSHKA-DC
    7. 1759
    Prev
    Next
    INDEX
    Explanations

    instances of assertion or commentary

    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
     noDo
    -0.91
    aarrggbb
    -0.91
    uxxxx
    -0.78
    TagHelper
    -0.76
    -};
    -0.70
     ब्रेकडाउन
    -0.70
    FormTagHelper
    -0.69
    InputBorder
    -0.67
    Bibliograf
    -0.67
     onCreateView
    -0.66
    POSITIVE LOGITS
     stated
    1.05
     said
    0.94
    said
    0.93
     explained
    0.86
     remarked
    0.84
     commented
    0.83
     claimed
    0.74
     mentioned
    0.74
     dijo
    0.71
     testified
    0.69
    Activations Density 1.363%

    No Known Activations