Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14166
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of unsafe code or operations

    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
     cherchés
    -0.93
    Tembelea
    -0.88
    <?
    -0.88
    WithIOException
    -0.88
     EconPapers
    -0.87
    rouvez
    -0.86
    tamol
    -0.85
    sizeCache
    -0.80
     RequestMethod
    -0.79
    Personendaten
    -0.79
    POSITIVE LOGITS
    unsafe
    2.34
    Unsafe
    0.70
     space
    0.44
     unsafe
    0.44
     too
    0.43
    ussen
    0.41
    yo
    0.41
     nos
    0.41
     Space
    0.40
    xAxis
    0.40
    Activations Density 0.002%

    No Known Activations