© 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. 6164
    Prev
    Next
    INDEX
    Explanations

    error messages related to email functionality and notification

    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
    يكب
    -0.75
    RESUMO
    -0.69
     виправивши
    -0.69
     متعلقه
    -0.68
    المشاركات
    -0.65
    حياته
    -0.64
     placental
    -0.63
     AssemblyCulture
    -0.60
     tilf
    -0.60
    :✨
    -0.59
    POSITIVE LOGITS
    +#+#
    0.55
    IBarButtonItem
    0.48
     you
    0.47
     Snackbar
    0.47
    Toaster
    0.46
     MessageBoxIcon
    0.46
    НС
    0.43
    خط
    0.43
     Pote
    0.41
    يميديا
    0.41
    Activations Density 0.188%

    No Known Activations