© 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. 790
    Prev
    Next
    INDEX
    Explanations

    action-related terms, particularly focusing on the concept of "move" in various forms

    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
     BeautifulSoup
    -0.77
     FirebaseAuth
    -0.65
     Qaeda
    -0.63
     Waugh
    -0.62
     HasFactory
    -0.62
    dao
    -0.59
     nacionais
    -0.59
    bao
    -0.58
    }</
    -0.57
     cathédrale
    -0.57
    POSITIVE LOGITS
     MOV
    1.74
     MOVE
    1.73
     moves
    1.71
     Moves
    1.70
     Move
    1.66
    Moved
    1.60
     move
    1.59
    Move
    1.59
    MOV
    1.56
     moved
    1.54
    Activations Density 0.324%

    No Known Activations