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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 30902
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, particularly involving variables and numerical data

    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
     {[
    -0.48
    Personendaten
    -0.48
    דות
    -0.47
     arrep
    -0.45
     Juegos
    -0.45
     épar
    -0.45
     Bogen
    -0.44
    عادة
    -0.44
     سبيل
    -0.44
     Lettuce
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.86
     كومونز
    0.66
    antMatchers
    0.66
     surla
    0.64
    出版年
    0.62
    IsPostBack
    0.61
    parsedMessage
    0.60
     UIImage
    0.59
    ("")]
    
    0.59
    WebElementEntity
    0.59
    Activations Density 0.061%

    No Known Activations