© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    words associated with trends and popularity

    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
    LLocation
    -0.64
    PreferredItem
    -0.64
    matchCondition
    -0.58
    rinhos
    -0.56
    stdc
    -0.55
     coupable
    -0.49
    mbres
    -0.49
    antigua
    -0.49
    structure
    -0.48
     peggio
    -0.48
    POSITIVE LOGITS
     popularity
    1.56
     Popularity
    1.32
     attracting
    1.20
     attract
    1.18
     popular
    1.16
    Popularity
    1.14
    popularity
    1.11
     garner
    1.10
     acclaim
    1.09
     notoriety
    1.09
    Activations Density 1.716%

    No Known Activations