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. 29970
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures

    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
     Tre
    -0.59
    ImageContext
    -0.57
    ẩm
    -0.55
    JAKARTA
    -0.55
     وتسجيلات
    -0.54
    oire
    -0.53
     cap
    -0.51
    gle
    -0.51
    madison
    -0.51
     Dreyfus
    -0.51
    POSITIVE LOGITS
    المناصب
    0.81
    webElementXpaths
    0.70
    createServer
    0.65
     otomatig
    0.64
    letoe
    0.60
     CWE
    0.60
     nonatomic
    0.59
     चीज़ों
    0.59
     Normdatei
    0.57
     ComVisible
    0.57
    Activations Density 0.078%

    No Known Activations