© 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. 2935
    Prev
    Next
    INDEX
    Explanations

    the word "terminate" and forms of it.

    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
    ugeot
    -0.77
     utafitiHapana
    -0.77
    +#+
    -0.74
     Мексичка
    -0.72
     springfox
    -0.69
     Invent
    -0.67
     فريبيس
    -0.67
     Hid
    -0.67
    jspx
    -0.66
     \]
    -0.66
    POSITIVE LOGITS
     terminated
    2.55
     terminate
    2.47
     termination
    2.34
     terminating
    2.19
     terminates
    2.14
     Termination
    2.11
    terminated
    2.09
    Termination
    2.05
    termination
    1.94
    terminate
    1.77
    Activations Density 0.012%

    No Known Activations