© 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. 1-RES-MATRYOSHKA-DC
    7. 553
    Prev
    Next
    INDEX
    Explanations

    instances of the word "break" used as a deliberate signal or command

    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
    UnknownFields
    -0.58
    upassen
    -0.57
    /*
    -0.57
    érêt
    -0.54
    awtextra
    -0.54
    ativistic
    -0.54
     kiệm
    -0.54
    Hozzáférés
    -0.52
    بالإنجليزية
    -0.52
     Wallflower
    -0.51
    POSITIVE LOGITS
     break
    4.94
    break
    4.75
     Break
    4.53
    Break
    4.34
     breaks
    4.28
     BREAK
    4.06
     breaking
    3.97
     Breaks
    3.86
     broke
    3.81
    BREAK
    3.80
    Activations Density 0.199%

    No Known Activations