© 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. 6126
    Prev
    Next
    INDEX
    Explanations

    elements related to police and scrutiny in discussions

    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
     Democrá
    -0.56
     Pues
    -0.55
     pranzo
    -0.50
     fermés
    -0.48
     dedans
    -0.47
     guste
    -0.47
     admir
    -0.46
     maniere
    -0.46
     liking
    -0.46
    effetto
    -0.45
    POSITIVE LOGITS
     SwitchCompat
    0.79
    脚注の使い方
    0.75
    kloped
    0.75
     Wikimédia
    0.73
     يتيمه
    0.69
     defaultstate
    0.69
    الحياه
    0.69
    qrstuvwxyz
    0.68
    sidemargin
    0.68
    ंदीखरीदारी
    0.64
    Activations Density 0.141%

    No Known Activations