© 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. 2-RES-MATRYOSHKA-DC
    7. 5711
    Prev
    Next
    INDEX
    Explanations

    the word "proper" in various contexts

    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
    relevant
    -0.86
     relevant
    -0.84
    saraba
    -0.81
     Relevant
    -0.80
    Relevant
    -0.79
    weeted
    -0.72
    chossen
    -0.72
     applicable
    -0.71
    priate
    -0.70
     SqlCommand
    -0.67
    POSITIVE LOGITS
     proper
    2.67
    proper
    2.66
     Proper
    2.58
    Proper
    2.52
     PROPER
    2.28
    properly
    1.78
     properly
    1.72
     Properly
    1.63
     improper
    1.45
     Improper
    1.34
    Activations Density 0.024%

    No Known Activations