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. 11830
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, names of organizations, and specific items in contexts of sports or legal frameworks

    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
    @[+][
    -0.73
    ViewFeatures
    -0.67
     Normdatei
    -0.63
     seguente
    -0.61
     BoxFit
    -0.59
     Himo
    -0.59
     endwhile
    -0.59
    
    -0.59
     generales
    -0.58
     שוליים
    -0.56
    POSITIVE LOGITS
    
    0.60
     Constipation
    0.60
     ſta
    0.59
     Quelles
    0.59
     paſſ
    0.57
     downg
    0.57
    はじめに
    0.56
    انجليز
    0.56
     pleaſure
    0.55
     againſt
    0.54
    Activations Density 0.270%

    No Known Activations