© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    quotes that convey excitement or positive sentiment about partnerships and support initiatives

    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
    Negative Logits
    arXiv
    -0.57
    TypeInfo
    -0.46
     Fuerzas
    -0.46
    Hauptartikel
    -0.45
    Արտաքին
    -0.44
    tudi
    -0.44
    atus
    -0.44
     gynnwys
    -0.43
     computer
    -0.43
     noDo
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.65
     estimés
    0.62
    HostException
    0.59
    CloseOperation
    0.58
    存于互联网档案馆
    0.57
    contentLoaded
    0.57
    GEBURTS
    0.57
     onBackPressed
    0.57
     SafeMath
    0.57
     AssemblyProduct
    0.56
    Activations Density 0.055%

    No Known Activations