© 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. 15061
    Prev
    Next
    INDEX
    Explanations

    passages that contain a strongly emphasized or explicitly stated stipulation or requirement

    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
     specify
    -1.39
     Specify
    -1.35
     specifying
    -1.18
    Specify
    -1.14
    specify
    -0.94
    +#+#
    -0.93
     specifies
    -0.79
     stipulation
    -0.65
    EndContext
    -0.64
    oa̍t
    -0.61
    POSITIVE LOGITS
     specified
    1.01
     stipulated
    0.87
    specified
    0.75
     selected
    0.68
     prescribed
    0.63
     given
    0.63
     Specified
    0.63
    ably
    0.62
    lielmo
    0.56
    instructor
    0.54
    Activations Density 0.003%

    No Known Activations