© 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. 11742
    Prev
    Next
    INDEX
    Explanations

    statements reflecting social insights or critiques on personal responsibility and societal issues

    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
    transQ
    -0.79
    verifyException
    -0.76
    ьаж
    -0.68
    المناصب
    -0.62
    İstinadlar
    -0.60
    '][$
    -0.57
    RTDA
    -0.55
    Хьажоргаш
    -0.54
     للتو
    -0.54
    FailureListener
    -0.53
    POSITIVE LOGITS
     myſelf
    0.67
     purpoſe
    0.65
     ſeveral
    0.65
     themſelves
    0.64
     fubject
    0.60
     juſ
    0.59
     pleaſure
    0.58
     raiſ
    0.57
     perfons
    0.57
     occaf
    0.56
    Activations Density 0.026%

    No Known Activations