© 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. 18-RES-MATRYOSHKA-DC
    7. 1635
    Prev
    Next
    INDEX
    Explanations

    scientific texts including parameters and symbols

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    DrawerToggle
    -0.49
    resizingMask
    -0.48
    SerializeField
    -0.45
    riko
    -0.43
     confec
    -0.41
    Хьажоргаш
    -0.41
    arian
    -0.41
    исленность
    -0.40
    behandling
    -0.38
     siku
    -0.38
    POSITIVE LOGITS
     kinetics
    1.05
     Rate
    0.86
     slowest
    0.85
    Rate
    0.84
     Kinetics
    0.83
     rate
    0.82
     enzyme
    0.81
     Reactions
    0.80
     Reaction
    0.79
    Reaction
    0.79
    Activations Density 1.355%

    No Known Activations