© 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. 0-RES-MATRYOSHKA-DC
    7. 11424
    Prev
    Next
    INDEX
    Explanations

    requests for leave or permission

    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
     departing
    -1.01
     departure
    -1.00
     exit
    -0.98
     departed
    -0.96
     exiting
    -0.94
     leaves
    -0.93
     leaving
    -0.91
     Leaving
    -0.91
    Leaving
    -0.89
     exited
    -0.89
    POSITIVE LOGITS
    leave
    1.34
     leave
    1.30
     Leave
    1.24
    Leave
    1.16
     LEAVE
    1.05
    expandindo
    0.96
    تقاوى
    0.79
     lenker
    0.78
     للمعارف
    0.76
    Hozzáférés
    0.76
    Activations Density 0.005%

    No Known Activations