© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15740
    Prev
    Next
    INDEX
    Explanations

    references to specific document identifiers and references

    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
     reference
    -1.19
     Reference
    -1.13
    Reference
    -1.04
    Refer
    -1.03
     References
    -0.99
     Refer
    -0.98
     references
    -0.98
     REFERENCE
    -0.95
     refer
    -0.93
    References
    -0.87
    POSITIVE LOGITS
    ref
    0.88
     }}"></
    0.70
    ming
    0.51
    
    0.50
     partij
    0.50
     aggiun
    0.49
    SuppressLint
    0.49
    rou
    0.49
    expandindo
    0.49
     durata
    0.49
    Activations Density 0.029%

    No Known Activations