© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 312
    Prev
    Next
    INDEX
    Explanations

    the contractions "I'm", "you're", "they're"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    让人
    -0.64
     comigo
    -0.63
     conmigo
    -0.63
     itself
    -0.59
    kháu
    -0.53
    DECREF
    -0.53
    讓人
    -0.53
    令人
    -0.52
     chod
    -0.52
    支
    -0.52
    POSITIVE LOGITS
     sure
    0.98
     glad
    0.98
     interested
    0.96
     afraid
    0.95
     surprised
    0.94
     amazed
    0.93
     curious
    0.91
     intrigued
    0.90
     worried
    0.88
     unsure
    0.87
    Activations Density 0.683%

    No Known Activations