© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    references to specific stipulations or agreements within legal or formal contractual language

    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
     specified
    -0.81
    extAlignment
    -0.70
    Portale
    -0.69
    ably
    -0.67
     selected
    -0.65
    specified
    -0.65
     թվական
    -0.64
    فایل‌لار
    -0.62
     سكانية
    -0.61
    hassee
    -0.61
    POSITIVE LOGITS
     specify
    1.53
     Specify
    1.51
    Specify
    1.31
     specifying
    1.18
    specify
    1.01
     specifies
    0.82
     OnTriggerEnter
    0.56
    AccessorTable
    0.54
    choose
    0.52
     préciser
    0.52
    Activations Density 0.002%

    No Known Activations