© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    words or short phrases connected by coordinating conjunctions like "and" or "or" that could represent lists or series of related ideas

    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
    ilina
    -0.51
    [](
    -0.51
    ashboard
    -0.51
    arja
    -0.50
    uha
    -0.50
    してみる
    -0.50
     Grab
    -0.49
    ╚
    -0.49
    果た
    -0.48
    Hit
    -0.48
    POSITIVE LOGITS
    reportWebVitals
    0.71
    AnimationsModule
    0.70
    rogens
    0.69
     defaultstate
    0.67
    المشاركات
    0.66
     kasarigan
    0.63
    Personensuche
    0.60
    PropertyChanging
    0.60
    WriteTagHelper
    0.60
    RegressionTest
    0.60
    Activations Density 0.707%

    No Known Activations