© 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. 1507
    Prev
    Next
    INDEX
    Explanations

    words related to roofing and construction

    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
    мять
    -0.59
     snippetHide
    -0.59
     nahilalakip
    -0.56
    apunov
    -0.55
    Personensuche
    -0.54
     cherchés
    -0.54
     AMOLED
    -0.52
    icznych
    -0.52
     utafiti
    -0.51
    bilirsiniz
    -0.50
    POSITIVE LOGITS
     installation
    1.05
     installing
    0.96
     install
    0.95
     installs
    0.93
     Installation
    0.92
     contractor
    0.89
     installers
    0.89
     installations
    0.88
     drywall
    0.88
     contractors
    0.87
    Activations Density 0.966%

    No Known Activations