© 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. 32081
    Prev
    Next
    INDEX
    Explanations

    significant advancements or breakthroughs in various fields

    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
     AspNetCore
    -0.52
    PRWEB
    -0.48
    neux
    -0.48
    bkz
    -0.47
     eventdata
    -0.47
     án
    -0.46
    usercontent
    -0.46
    sique
    -0.46
     sus
    -0.45
    WebControls
    -0.45
    POSITIVE LOGITS
     breakthrough
    1.02
     milestone
    0.90
     landmark
    0.88
    Landmark
    0.87
     breakthroughs
    0.86
     advancements
    0.83
    milestone
    0.82
    complishments
    0.80
    landmark
    0.80
     Landmark
    0.80
    Activations Density 0.081%

    No Known Activations