© 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. 3142
    Prev
    Next
    INDEX
    Explanations

    expressions of apology or regret

    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
     reak
    -0.53
    kjø
    -0.52
     sugges
    -0.50
    styleType
    -0.50
     proc
    -0.49
     Chuck
    -0.49
     reaction
    -0.47
    ViewFeatures
    -0.47
    енча
    -0.47
     conversation
    -0.47
    POSITIVE LOGITS
     sorry
    3.69
     Sorry
    3.05
     SORRY
    3.05
    sorry
    2.95
    Sorry
    2.73
     apologies
    2.11
     apologize
    1.99
     apologise
    1.95
     apology
    1.94
    Apologies
    1.88
    Activations Density 0.013%

    No Known Activations