© 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. 29946
    Prev
    Next
    INDEX
    Explanations

    phrases related to dependencies and relationships between elements in a data 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
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.66
    WebControls
    -0.62
    LabelTagHelper
    -0.60
     meanwhile
    -0.55
     AssemblyCompany
    -0.55
     مواليد
    -0.54
    ]={
    -0.52
    horesis
    -0.52
    ☆☆☆☆
    -0.51
    참고
    -0.49
    POSITIVE LOGITS
     ONLY
    0.73
     only
    0.71
    only
    0.71
     تضيفلها
    0.69
    IonicModule
    0.65
     uniquement
    0.62
    ONLY
    0.61
    Only
    0.61
     seulement
    0.60
     tylko
    0.60
    Activations Density 0.204%

    No Known Activations