© 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. 20923
    Prev
    Next
    INDEX
    Explanations

    Java and Android programming concepts, particularly related to classes and UI elements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    getChannel
    -0.50
     Edge
    -0.49
    foglal
    -0.49
    جغرافيا
    -0.48
     sigma
    -0.48
    alaman
    -0.46
     Ahu
    -0.46
    sette
    -0.46
    atería
    -0.46
    MLLoader
    -0.46
    POSITIVE LOGITS
     ControllerBase
    0.91
     AppCompat
    0.90
     StatefulWidget
    0.90
     MonoBehaviour
    0.87
     JpaRepository
    0.79
     StatelessWidget
    0.76
     كومونز
    0.76
    UrlResolution
    0.74
     XCTest
    0.71
     BaseActivity
    0.66
    Activations Density 0.002%

    No Known Activations