© 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. 22-RES-MATRYOSHKA-DC
    7. 2939
    Prev
    Next
    INDEX
    Explanations

    scientific research articles

    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.22.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.22.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
     summarise
    -0.54
    ագրություններ
    -0.53
     summarize
    -0.51
    IOL
    -0.51
    ecutive
    -0.50
    AMPLE
    -0.49
     Summar
    -0.49
     vertrouwen
    -0.49
    eraard
    -0.49
    tiliz
    -0.49
    POSITIVE LOGITS
     show
    1.20
    show
    1.16
     shown
    1.13
     Showing
    1.13
     showing
    1.11
    Show
    1.10
    Showing
    1.10
     demonstrate
    1.08
     Show
    1.05
    showing
    1.02
    Activations Density 0.415%

    No Known Activations