© 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. 8786
    Prev
    Next
    INDEX
    Explanations

    indicators of potential medical or health conditions through relationships and associations described in research data

    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
    ]")]
    -0.80
    ()]);
    -0.68
    ::::::::::::::::
    -0.60
    цездатний
    -0.60
    AsUp
    -0.59
    ніципа
    -0.59
    ThemeOverlay
    -0.57
     lenker
    -0.53
     betweenstory
    -0.52
    '){
    -0.52
    POSITIVE LOGITS
    EndContext
    0.66
    DockStyle
    0.60
    Jegyzetek
    0.58
     Paglinawan
    0.57
    DebuggerNonUser
    0.55
    はじめに
    0.55
    Bronnen
    0.53
    oa̍t
    0.52
    σθαι
    0.52
    culin
    0.52
    Activations Density 0.140%

    No Known Activations