© 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. 7986
    Prev
    Next
    INDEX
    Explanations

    references to scientific inventions and their applications

    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
    ogia
    -0.72
     '{@
    -0.63
     ujednoznacz
    -0.62
    PerformLayout
    -0.59
     <>",
    -0.59
    TELL
    -0.56
    getCmp
    -0.56
    cèse
    -0.55
    adget
    -0.55
     ©️
    -0.54
    POSITIVE LOGITS
    出版年
    0.58
    <tfoot>
    0.56
     ModelExpression
    0.56
    Sprintf
    0.51
    الإنجليزية
    0.51
     createContext
    0.47
    istoitu
    0.45
     messaggio
    0.44
     Zayed
    0.44
     TAMBÉM
    0.44
    Activations Density 0.167%

    No Known Activations