© 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. 5474
    Prev
    Next
    INDEX
    Explanations

    references to specific legal or scientific terminology and cases

    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
    ⟩
    -0.46
    łby
    -0.43
    ">'+
    -0.42
     despedida
    -0.41
    شي
    -0.40
     video
    -0.39
    legd
    -0.38
     croy
    -0.38
     newly
    -0.37
    šanai
    -0.37
    POSITIVE LOGITS
    sizeCache
    0.95
    PerformLayout
    0.88
    RegressionTest
    0.83
    ChildScrollView
    0.81
    ⓧ
    0.81
     مشين
    0.79
     ExecuteAsync
    0.79
     Normdatei
    0.78
    Hentet
    0.78
    DoubleQuotes
    0.76
    Activations Density 0.454%

    No Known Activations