© 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. 24440
    Prev
    Next
    INDEX
    Explanations

    statistical terms and indicators of significance in research data

    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
     NSError
    -0.56
    ☸
    -0.48
     pictogram
    -0.45
    blico
    -0.45
     stuks
    -0.44
    ushman
    -0.44
    assertThrows
    -0.44
    RuntimeObject
    -0.42
    AndroidJUnit
    -0.42
     fiancé
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.77
     kaarangay
    0.67
    AnimationsModule
    0.65
     rhestr
    0.64
     Мексичка
    0.63
    Tikang
    0.63
    AutoresizingMask
    0.63
     pinulongan
    0.61
     محفوظة
    0.60
    tagext
    0.60
    Activations Density 0.009%

    No Known Activations