© 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. 18-RES-MATRYOSHKA-DC
    7. 1380
    Prev
    Next
    INDEX
    Explanations

    words that describe a scholarly article or scientific findings

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    MLLoader
    -0.69
    Referanser
    -0.63
    ecause
    -0.59
     ujednoznacz
    -0.57
     niin
    -0.57
    ----</
    -0.56
     quanto
    -0.52
     "",
    -0.51
    standers
    -0.50
     conformément
    -0.50
    POSITIVE LOGITS
    MessageOf
    0.56
    IndentedString
    0.52
     bowiem
    0.51
    isDebugEnabled
    0.51
     Réponses
    0.50
     @"/
    0.50
    ,
    0.49
    市镇
    0.48
    ISupport
    0.48
    providedIn
    0.48
    Activations Density 0.839%

    No Known Activations