© 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. 6556
    Prev
    Next
    INDEX
    Explanations

    terms related to hydrogen and its compounds

    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
    ImageContext
    -0.90
     
    -0.83
    verwijspagina
    -0.77
     LEP
    -0.74
    awtextra
    -0.72
     Warlock
    -0.71
     Mathis
    -0.70
     Faul
    -0.70
     Bettina
    -0.70
     Exo
    -0.69
    POSITIVE LOGITS
    hydrogen
    1.14
    Hydrogen
    1.12
     hydrogen
    1.10
     Hydrogen
    0.98
    LookAnd
    0.85
     Wasserstoff
    0.72
    proton
    0.68
     proton
    0.63
     protons
    0.61
    Proton
    0.59
    Activations Density 0.035%

    No Known Activations