© 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. 5522
    Prev
    Next
    INDEX
    Explanations

    words indicating relevance or importance in legal or judicial context

    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
    proper
    -1.15
     proper
    -1.11
     Proper
    -1.06
    Proper
    -1.00
     PROPER
    -0.98
     خارجية
    -0.91
    properly
    -0.89
     improper
    -0.87
     properly
    -0.85
     Properly
    -0.84
    POSITIVE LOGITS
    relevant
    2.23
     relevant
    2.17
     Relevant
    2.09
    Relevant
    2.06
     relevance
    1.89
     Relevance
    1.79
    Relevance
    1.65
    LEVANT
    1.63
    relevance
    1.59
     relevan
    1.56
    Activations Density 0.021%

    No Known Activations