© 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. 25578
    Prev
    Next
    INDEX
    Explanations

    elements related to Android UI layout attributes and configurations

    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
     doInBackground
    -0.66
     disponibilités
    -0.59
    requireNonNull
    -0.59
     purpoſe
    -0.56
    rency
    -0.56
     Normdatei
    -0.54
     ویکی‌پدیا
    -0.54
     laiton
    -0.54
     vro
    -0.52
    قة
    -0.52
    POSITIVE LOGITS
    "}")
    0.66
    soka
    0.64
    --)
    0.59
    PMailer
    0.59
    colnshire
    0.58
     Huck
    0.57
    timewa
    0.57
    opcional
    0.56
    逅
    0.56
    riwal
    0.56
    Activations Density 0.018%

    No Known Activations