© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17396
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate announcements or significant updates regarding products, particularly in the context of new motorcycle models

    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
    expandindo
    -0.75
     propOrder
    -0.72
     femininas
    -0.69
    ########.
    -0.69
     InputDecoration
    -0.68
    ungkinan
    -0.66
     normaux
    -0.65
     समीक्षक
    -0.64
     onOptions
    -0.63
     esternos
    -0.63
    POSITIVE LOGITS
    hint
    0.65
     surprises
    0.57
     surprise
    0.56
     secrets
    0.56
     secret
    0.56
     reveal
    0.54
    🤫
    0.54
     unveil
    0.54
     revealed
    0.52
     hinted
    0.51
    Activations Density 0.095%

    No Known Activations