© 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. 30958
    Prev
    Next
    INDEX
    Explanations

    terms related to tactics and strategic actions

    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
    
    -1.00
    出版年
    -0.90
     nahilalakip
    -0.90
    RemoveField
    -0.81
    SpringBootTest
    -0.77
    parsedMessage
    -0.77
     alberi
    -0.76
     Cataloging
    -0.75
     surla
    -0.75
     &___
    -0.75
    POSITIVE LOGITS
    tics
    0.97
     Kig
    0.89
    nics
    0.87
    `;
    0.78
     Becca
    0.77
    ¹)
    0.77
    ”،
    0.76
     optics
    0.75
     ſeveral
    0.75
     ſame
    0.74
    Activations Density 0.144%

    No Known Activations