© 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. 9424
    Prev
    Next
    INDEX
    Explanations

    references to minerals in various contexts

    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
     Quito
    -0.85
     Kome
    -0.81
     roulant
    -0.80
     Volga
    -0.79
     Jind
    -0.77
    fromCharCode
    -0.72
     SRT
    -0.71
     Sosten
    -0.71
    IActionResult
    -0.70
     Suz
    -0.70
    POSITIVE LOGITS
     mineral
    1.27
     minerals
    1.27
     Mineral
    1.23
     Minerals
    1.17
    Minerals
    1.16
     MINERAL
    1.12
    mineral
    1.09
    Mineral
    1.07
    miner
    1.00
     minerales
    0.94
    Activations Density 0.004%

    No Known Activations