© 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. 13996
    Prev
    Next
    INDEX
    Explanations

    terms related to prior preparation and association in various contexts

    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
     كومونز
    -1.02
    DockStyle
    -0.95
     '\\;'
    -0.95
    InputBorder
    -0.93
     NSCoder
    -0.85
     lenker
    -0.84
     ComVisible
    -0.83
    sidemargin
    -0.81
    
    -0.79
    BeginContext
    -0.77
    POSITIVE LOGITS
    Pre
    1.12
     Pre
    1.05
     pre
    0.98
     PRE
    0.94
    PRE
    0.93
    pre
    0.93
    预
    0.86
     pré
    0.83
     预
    0.79
     preload
    0.78
    Activations Density 0.054%

    No Known Activations