© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that someone should do or verify something

    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
     Sache
    -0.48
    UnknownFieldSet
    -0.46
    <table>
    -0.44
    edy
    -0.44
    浅
    -0.44
    <i>
    -0.44
     meas
    -0.42
    ADA
    -0.42
    meas
    -0.42
    w
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.94
    GraphicsUnit
    0.88
    ,:)
    0.85
    WriteBarrier
    0.84
     الاطلاع
    0.84
    GeneratedValue
    0.84
    tagHelperRunner
    0.83
    تقاوى
    0.82
    ẨM
    0.80
    .*")]
    0.79
    Activations Density 0.009%

    No Known Activations