© 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. 30098
    Prev
    Next
    INDEX
    Explanations

    references to quantum mechanics experiments and their relevant variables

    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
     CreateTagHelper
    -0.64
    RegressionTest
    -0.62
    ThroughAttribute
    -0.57
    abin
    -0.53
     Treat
    -0.52
     onAnimation
    -0.52
     Biôgrafia
    -0.52
     utafitiHapana
    -0.52
     &___
    -0.51
     betweenstory
    -0.51
    POSITIVE LOGITS
    ContentAsync
    0.60
    NewGuid
    0.51
    abestanden
    0.51
    yttö
    0.51
    fromString
    0.49
    UIControlState
    0.48
    sonar
    0.47
    DockStyle
    0.47
     onyx
    0.46
     Helene
    0.46
    Activations Density 0.013%

    No Known Activations