© 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. 26964
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and code structure

    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
     chré
    -0.73
     pleaſure
    -0.72
     चीज़ों
    -0.69
     Efq
    -0.69
     myſelf
    -0.68
     quæ
    -0.68
     poffible
    -0.66
     purpoſe
    -0.64
     pouvoit
    -0.64
     ainfi
    -0.62
    POSITIVE LOGITS
    WebElementEntity
    0.65
    BagLayout
    0.59
    WebControls
    0.59
     lit
    0.58
    providedIn
    0.52
    netbeans
    0.51
    ئ
    0.51
    Carreira
    0.50
     mat
    0.50
    rophoresis
    0.50
    Activations Density 0.102%

    No Known Activations