© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30728
    Prev
    Next
    INDEX
    Explanations

    specific formatting or presentation details such as data structures or attributes in text

    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
    Negative Logits
    expandindo
    -0.63
    FieldBuilder
    -0.60
    Xaml
    -0.59
    favorited
    -0.59
     архивлан
    -0.59
    
    -0.54
    SpringBoot
    -0.54
    ScopeManager
    -0.54
    dawnictwo
    -0.54
    QMetaType
    -0.53
    POSITIVE LOGITS
    ttemberg
    0.54
    μένες
    0.52
    espé
    0.49
    MeasureSpec
    0.49
    Насе
    0.49
    تقاوى
    0.49
    SizeMode
    0.49
    cipais
    0.47
    ioutil
    0.45
    …»
    0.45
    Activations Density 0.153%

    No Known Activations