© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 513
    Prev
    Next
    INDEX
    Explanations

    numbers starting with 4 or 5

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    postIndex
    -0.66
     ألف
    -0.63
    resave
    -0.62
     وتسجيلات
    -0.60
     متعلقه
    -0.60
     استنادى
    -0.55
    posedge
    -0.54
     विश्वसनीयता
    -0.54
    anyol
    -0.54
    LabelTagHelper
    -0.54
    POSITIVE LOGITS
    ️⃣
    0.89
    ⃣
    0.75
    つの
    0.75
    ":[{
    0.69
     continents
    0.66
     tenths
    0.59
    findpost
    0.59
     Senses
    0.59
    orological
    0.57
     @"/
    0.57
    Activations Density 2.090%

    No Known Activations