© 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. 22-RES-MATRYOSHKA-DC
    7. 3066
    Prev
    Next
    INDEX
    Explanations

    information or phrases related to toxicity studies in rats, reporting levels and durations, including acronyms like NOAEL and endpoints like fertility or development

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     campers
    -0.62
     emis
    -0.59
    MapView
    -0.56
     polu
    -0.56
    Pollution
    -0.53
     Illegal
    -0.53
    Illegal
    -0.52
    Medicare
    -0.50
     onCreateView
    -0.50
     contamination
    -0.50
    POSITIVE LOGITS
    OECD
    0.60
     OECD
    0.59
    kloped
    0.58
     pinulongan
    0.57
     Normdatei
    0.56
    ratto
    0.55
     Geno
    0.54
     endpoints
    0.54
     endpoint
    0.53
     gynhyrchwyd
    0.53
    Activations Density 0.208%

    No Known Activations