© 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. 18-RES-MATRYOSHKA-DC
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    mentions of code or programming that works or doesn't work

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    MemoryWarning
    -0.80
    BeginContext
    -0.73
    LabelTagHelper
    -0.69
    ^(@)
    -0.69
    ngdoc
    -0.68
     pinulongan
    -0.67
    XMLSchema
    -0.66
    AndEndTag
    -0.66
    PerformLayout
    -0.65
    uxxxx
    -0.64
    POSITIVE LOGITS
     works
    1.16
     worked
    1.08
    Works
    1.06
     funziona
    1.06
     funzion
    1.05
     funciona
    1.05
     funktioniert
    1.03
     succeed
    1.02
     succeeds
    1.02
     successful
    1.02
    Activations Density 1.085%

    No Known Activations