© 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. 30258
    Prev
    Next
    INDEX
    Explanations

    terms related to uprisings or rebellions

    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
     paramInt
    -0.60
     Bag
    -0.60
    Crap
    -0.60
     fog
    -0.57
     rar
    -0.57
    shit
    -0.56
    ficador
    -0.56
     للاسماء
    -0.56
     snuff
    -0.55
    CppMethod
    -0.54
    POSITIVE LOGITS
     rebels
    1.32
     rebel
    1.31
     rebellion
    1.28
    rebel
    1.24
     Rebel
    1.20
    Rebel
    1.20
     Rebellion
    1.17
     Rebels
    1.15
     rebellious
    1.07
     revolt
    1.04
    Activations Density 0.024%

    No Known Activations