© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    terms related to opportunities and functionalities in technology or healthcare contexts

    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
     محفوظة
    -0.90
    CppMethod
    -0.85
    存于互联网档案馆
    -0.82
     ویکی‌پدیا
    -0.80
     pinulongan
    -0.74
     bezeichneter
    -0.68
    Hentet
    -0.68
     AssemblyCulture
    -0.67
     تضيفلها
    -0.65
     Normdatei
    -0.65
    POSITIVE LOGITS
     etc
    0.75
    etc
    0.75
     Etc
    0.60
    withstanding
    0.52
     Efq
    0.51
    づ
    0.51
     porém
    0.50
     Porém
    0.50
     itp
    0.49
     Huse
    0.49
    Activations Density 0.150%

    No Known Activations