© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29742
    Prev
    Next
    INDEX
    Explanations

    function calls and data manipulation in programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.59
    bledon
    -0.54
    URLConnection
    -0.50
    sphase
    -0.49
    otimes
    -0.46
    areth
    -0.46
    fromnode
    -0.45
    lawayo
    -0.43
    beek
    -0.42
    tonode
    -0.41
    POSITIVE LOGITS
    expandindo
    0.75
     kaynağından
    0.72
    modelBuilder
    0.63
     برانيه
    0.63
    TLE
    0.61
     themſelves
    0.60
    XmlAccessorType
    0.59
     Савезне
    0.59
     vedi
    0.57
    ValueGeneration
    0.57
    Activations Density 0.119%

    No Known Activations