© 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. 13515
    Prev
    Next
    INDEX
    Explanations

    references to spam or unsolicited promotional messages

    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
    CloseOperation
    -0.84
     للمعارف
    -0.83
    writeFieldEnd
    -0.72
    +#+#
    -0.67
     '\\;'
    -0.66
     CWE
    -0.65
    Dữ
    -0.63
     TextAlign
    -0.63
     autorytatywna
    -0.62
    ypeł
    -0.60
    POSITIVE LOGITS
     spo
    3.16
     SPO
    2.98
    Spo
    2.97
     Spo
    2.89
    spo
    2.81
    SPO
    2.11
     spool
    1.41
     spoil
    1.27
     spoiled
    1.20
     Spokes
    1.20
    Activations Density 0.002%

    No Known Activations