© 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. 3050
    Prev
    Next
    INDEX
    Explanations

    expressions of completeness 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
    Complete
    -1.05
     complete
    -1.03
    complete
    -1.02
     entire
    -1.00
     Complete
    -1.00
     whole
    -0.96
     COMPLETE
    -0.92
     Efq
    -0.91
     becauſe
    -0.91
     total
    -0.84
    POSITIVE LOGITS
     fully
    2.45
     Fully
    2.42
    Fully
    2.30
    fully
    1.51
    FULLY
    1.45
     pleinement
    1.42
     plenamente
    1.38
     sepenuhnya
    1.00
     fullt
    0.92
     entièrement
    0.90
    Activations Density 0.015%

    No Known Activations