© 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. 21185
    Prev
    Next
    INDEX
    Explanations

    references to connectivity and transportation developments

    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
    OGND
    -0.59
     BoxFit
    -0.59
    LEncoder
    -0.56
    GrantedAuthority
    -0.53
    Gön
    -0.52
    display
    -0.52
    setFlags
    -0.50
     subsoil
    -0.50
    zept
    -0.49
     onAnimation
    -0.48
    POSITIVE LOGITS
    はじめに
    0.52
    buzo
    0.50
    RegressionTest
    0.50
    UnsafeEnabled
    0.50
     समीक्षक
    0.50
     EClass
    0.48
    ChildIndex
    0.48
     հղումներ
    0.47
    }();
    0.47
    országban
    0.47
    Activations Density 1.132%

    No Known Activations