© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28557
    Prev
    Next
    INDEX
    Explanations

    terms that emphasize the value and importance of life or cherished items

    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
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.98
    RRect
    -0.68
    Off
    -0.67
     Off
    -0.66
    لاقات
    -0.66
    Gust
    -0.62
    setVerticalGroup
    -0.62
    ußen
    -0.59
    
    -0.59
     Hewitt
    -0.58
    POSITIVE LOGITS
     treasure
    1.38
     TREAS
    1.32
     Treasure
    1.29
     treasures
    1.27
    Treasure
    1.27
     Precious
    1.17
     Treasures
    1.14
     precious
    1.13
    treasure
    1.12
     treasured
    1.05
    Activations Density 0.010%

    No Known Activations