© 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. 5491
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer engagement and product recommendations

    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
    <eos>
    -0.57
      
    -0.47
     We
    -0.44
    *
    -0.43
    ↵
    -0.43
    ↵↵↵
    -0.42
     bize
    -0.42
    <strong>
    -0.42
     
    -0.42
    ...
    -0.42
    POSITIVE LOGITS
     '\\;'
    1.07
    :✨
    0.96
    -------------</
    0.93
    UserScript
    0.93
    skjaer
    0.90
     itſelf
    0.89
     myſelf
    0.89
     purpoſe
    0.87
     yourself
    0.85
    ----</
    0.84
    Activations Density 0.305%

    No Known Activations