© 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. 20552
    Prev
    Next
    INDEX
    Explanations

    elements related to programming function definitions and their parameters

    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
    UrlResolution
    -0.90
    GraphicsUnit
    -0.85
    PerformLayout
    -0.79
    ViewChild
    -0.78
    providedIn
    -0.76
    useNewUrlParser
    -0.76
     gynhyrchwyd
    -0.75
    __":
    -0.73
    createCanvas
    -0.73
     الرياضيه
    -0.72
    POSITIVE LOGITS
     ilman
    0.49
    хран
    0.46
     iniziale
    0.42
     abstrait
    0.41
     boissons
    0.41
     suure
    0.41
     cherchez
    0.40
     før
    0.40
     before
    0.40
     carrés
    0.39
    Activations Density 0.050%

    No Known Activations