© 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. 18-RES-MATRYOSHKA-DC
    7. 596
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the legal system and prisons

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    VERTISING
    -0.62
    apimachinery
    -0.58
     surla
    -0.56
    Synonymes
    -0.52
    saraba
    -0.51
    PRNewswire
    -0.46
    Market
    -0.45
    webdriver
    -0.45
     Bühne
    -0.44
    vensko
    -0.44
    POSITIVE LOGITS
     prison
    1.67
     Prison
    1.58
     prisoner
    1.58
     inmate
    1.55
     prisoners
    1.54
    Prison
    1.51
     inmates
    1.50
    prison
    1.47
     prisons
    1.45
     PRISON
    1.38
    Activations Density 1.720%

    No Known Activations