© 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. 22397
    Prev
    Next
    INDEX
    Explanations

    JavaScript console commands and alert functions

    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
     Stel
    -0.50
     aufgestellt
    -0.48
     Worn
    -0.48
    ФОР
    -0.47
     QtGui
    -0.47
    GetMapping
    -0.46
    </tr>
    -0.46
    Einzelnachweise
    -0.46
    WithFormat
    -0.46
    PostMapping
    -0.45
    POSITIVE LOGITS
     AssemblyVersion
    0.74
    ButterKnife
    0.65
     RIPRODUZIONE
    0.58
     AssemblyCompany
    0.57
     numberOfRows
    0.54
    fromCharCode
    0.52
     NDEBUG
    0.52
     considérons
    0.52
    Билгалдахарш
    0.52
    Diwedd
    0.51
    Activations Density 0.018%

    No Known Activations