© 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. 10131
    Prev
    Next
    INDEX
    Explanations

    terms related to warning signs and yield indicators in traffic contexts

    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
    PerformLayout
    -0.73
     Мексичка
    -0.71
     IndexPath
    -0.67
    IUrlHelper
    -0.67
     cherchés
    -0.60
    URLException
    -0.59
    ädie
    -0.59
    verifyException
    -0.59
    djangoproject
    -0.58
     EClass
    -0.58
    POSITIVE LOGITS
     Meldung
    0.50
     engaged
    0.48
     parkir
    0.48
     fondé
    0.48
     pregă
    0.47
     fondée
    0.47
    engage
    0.46
     Donner
    0.46
    carril
    0.46
    చు
    0.46
    Activations Density 0.038%

    No Known Activations