© 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. 11644
    Prev
    Next
    INDEX
    Explanations

    phrases related to the acquisition of materials or substances

    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
    ollectionView
    -0.81
    MLLoader
    -0.75
    AnimationsModule
    -0.72
    ſelf
    -0.71
     فريبيس
    -0.70
    Réalisation
    -0.70
    MemoryWarning
    -0.65
    tagHelperRunner
    -0.64
    StoryboardSegue
    -0.63
     AspNetCore
    -0.62
    POSITIVE LOGITS
     Freiheit
    0.48
     filosó
    0.48
     Freedom
    0.45
    ศ
    0.45
    migrations
    0.44
    estones
    0.44
     Glaube
    0.44
    月初
    0.44
    ற்ற
    0.44
     supermercados
    0.44
    Activations Density 0.009%

    No Known Activations