© 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. 30531
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions, actions, or situations related to the use or exposure of substances

    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
    ViewFeatures
    -0.80
     CreateTagHelper
    -0.80
     propOrder
    -0.79
     NSCoder
    -0.69
    Попис
    -0.67
    клопе
    -0.65
     NgModule
    -0.65
    parsedMessage
    -0.65
    AddTagHelper
    -0.63
    zarchiwizowane
    -0.61
    POSITIVE LOGITS
    toHave
    0.57
     BoxDecoration
    0.57
     disambiguazione
    0.57
    Viitteet
    0.52
    mph
    0.48
    θούν
    0.48
     didst
    0.48
    chées
    0.48
     nullptr
    0.47
    AYO
    0.47
    Activations Density 0.152%

    No Known Activations