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. 31868
    Prev
    Next
    INDEX
    Explanations

    terms related to bacterial classification and categorization, specifically focusing on gram-positive and gram-negative bacteria

    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
     Maintenant
    -0.50
    iastes
    -0.50
     <<<<<<<<<<<<<<
    -0.50
    ieszcz
    -0.50
     Sagan
    -0.48
     pilot
    -0.48
     Afraid
    -0.48
    ycznie
    -0.47
    isNotBlank
    -0.47
    addComponent
    -0.47
    POSITIVE LOGITS
     الحره
    0.76
    tagHelperRunner
    0.70
    исленность
    0.69
    PMailer
    0.69
    ChildScrollView
    0.66
    parsedMessage
    0.65
    StoreMessageInfo
    0.63
    makeConstraints
    0.63
     ostavi
    0.57
    χρι
    0.57
    Activations Density 0.109%

    No Known Activations