© 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. 24-RES-MATRYOSHKA-DC
    7. 1627
    Prev
    Next
    INDEX
    Explanations

    scientific measurements, in units of mg or kg, administered via IP injection, over a period of days or weeks

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    GOTREF
    -0.68
     désolés
    -0.63
     Vikipedi
    -0.62
    migrationBuilder
    -0.60
    msgTypes
    -0.59
     planas
    -0.56
     оригіналу
    -0.56
     ProtoMessage
    -0.55
     tartalomajánló
    -0.55
     autorytatywna
    -0.54
    POSITIVE LOGITS
     injection
    0.93
     inject
    0.81
     injected
    0.81
     intramuscular
    0.81
     Injection
    0.79
     injections
    0.78
    Administ
    0.77
     administration
    0.77
     admin
    0.76
     intra
    0.74
    Activations Density 0.650%

    No Known Activations