© 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. 10656
    Prev
    Next
    INDEX
    Explanations

    syntactic constructs and programming structures in code snippets

    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
    lunda
    -0.81
    ^(@)
    -0.68
    aarrggbb
    -0.66
     dévelo
    -0.65
    ayage
    -0.65
     BoxFit
    -0.64
    ItemBackground
    -0.64
     Sted
    -0.63
     homeland
    -0.62
     MonoBehaviour
    -0.60
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.66
     ạ
    0.59
    principalTable
    0.56
    newBuilder
    0.52
     initComponents
    0.52
    XmlEnum
    0.46
    ENDIF
    0.43
    '}>
    0.43
     }?>
    0.43
    arsus
    0.42
    Activations Density 0.026%

    No Known Activations