© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    uses of academic language to explain scientific results.

    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
    ActionBar
    -0.57
     detecting
    -0.54
    ANTLR
    -0.50
    NewGuid
    -0.49
     discovering
    -0.49
    انيف
    -0.48
    AutoSize
    -0.48
     '\\;'
    -0.47
     directed
    -0.47
     discover
    -0.47
    POSITIVE LOGITS
     models
    1.43
     model
    1.38
     Models
    1.27
    models
    1.25
     modeling
    1.23
    model
    1.20
    モデル
    1.20
     modelos
    1.19
     MODELS
    1.19
     MODEL
    1.17
    Activations Density 1.613%

    No Known Activations