© 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. 1733
    Prev
    Next
    INDEX
    Explanations

    the word "completely."

    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
     accordingly
    -0.71
     saites
    -0.71
     Mittel
    -0.66
     estekak
    -0.66
     respectivement
    -0.65
    respectively
    -0.65
     ironically
    -0.65
     Onions
    -0.65
     selaku
    -0.64
     Peu
    -0.64
    POSITIVE LOGITS
     completely
    2.88
     Completely
    2.66
    Completely
    2.59
    completely
    2.50
     totally
    2.39
     complete
    2.36
    Complete
    2.23
     entirely
    2.20
     Complete
    2.17
     COMPLE
    2.17
    Activations Density 0.477%

    No Known Activations