© 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. 23186
    Prev
    Next
    INDEX
    Explanations

    legal or official actions and recommendations

    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
     Réponses
    -0.68
     beginnetje
    -0.62
    Derbyniad
    -0.58
    BeginInit
    -0.57
    Portail
    -0.56
    -0.53
    Kjelder
    -0.52
    hogy
    -0.51
    expandindo
    -0.51
    setVerticalGroup
    -0.51
    POSITIVE LOGITS
    agno
    0.56
    \|_{\
    0.55
    esistenza
    0.55
    enumi
    0.53
    DoubleQuotes
    0.53
     обращения
    0.51
    БЕ
    0.51
    alom
    0.50
    artin
    0.50
     yuan
    0.49
    Activations Density 0.260%

    No Known Activations