© 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. 12-RES-MATRYOSHKA-DC
    7. 23168
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly focusing on certain quantities and their relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ühungen
    -0.71
    Personendaten
    -0.69
    MessageOf
    -0.68
    Datuak
    -0.67
    
    -0.67
    UnsafeEnabled
    -0.66
     مشين
    -0.66
     hessen
    -0.65
    WebVitals
    -0.65
    Allo
    -0.65
    POSITIVE LOGITS
    Résumé
    0.52
    EnableWeb
    0.48
    äj
    0.47
    makeConstraints
    0.44
     Silverman
    0.44
    confirmButton
    0.43
    RESUME
    0.43
    uninstall
    0.42
    hedrals
    0.42
    mení
    0.42
    Activations Density 0.035%

    No Known Activations