© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8544
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names, brands, and organizations

    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
     समीक्षाएं
    -0.57
    (&:
    -0.52
    MMV
    -0.50
    vil
    -0.49
     jadx
    -0.48
    
    -0.48
     useAuth
    -0.48
     AssemblyCompany
    -0.48
    httphttps
    -0.46
    w
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.80
     ModelExpression
    0.73
     itſelf
    0.73
    >\<^
    0.69
    WEBPACK
    0.68
    UNICIP
    0.67
    FieldBuilder
    0.65
    ypeł
    0.64
     wireType
    0.63
    \<^
    0.62
    Activations Density 0.121%

    No Known Activations