© 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. 30685
    Prev
    Next
    INDEX
    Explanations

    terms related to immersion and the act of being soaked in a substance

    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
     Figueroa
    -0.72
    theon
    -0.71
    Syl
    -0.66
     GenerationType
    -0.63
    :✨
    -0.62
     Fox
    -0.62
     windy
    -0.61
     lắp
    -0.61
    rety
    -0.60
     Teig
    -0.59
    POSITIVE LOGITS
     immersion
    1.38
     immersed
    1.33
     Immersion
    1.30
    Dip
    1.27
     dip
    1.17
     Dip
    1.17
     dipped
    1.16
     immers
    1.16
    immer
    1.14
     dipping
    1.14
    Activations Density 0.022%

    No Known Activations