© 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. 12-RES-MATRYOSHKA-DC
    7. 19611
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases expressing curiosity or seeking confirmation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.73
    addCriterion
    -0.71
    MENAFN
    -0.66
     himo
    -0.64
     EconPapers
    -0.62
     transférez
    -0.61
     Saltar
    -0.61
    WireFormatLite
    -0.60
    хьтан
    -0.59
    urlpatterns
    -0.57
    POSITIVE LOGITS
     nho
    0.55
     Agree
    0.54
    gwin
    0.54
     tiến
    0.54
     препратки
    0.53
    ILO
    0.53
    
    0.53
     برانيه
    0.52
     colectivo
    0.51
    payee
    0.50
    Activations Density 0.013%

    No Known Activations