© 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. 23554
    Prev
    Next
    INDEX
    Explanations

    terms related to legal convictions and sentencing in criminal cases

    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
    Negative Logits
     quem
    -0.45
     who
    -0.45
     Crime
    -0.42
    挙
    -0.42
     convict
    -0.42
     kunt
    -0.41
    \|\
    -0.41
     escote
    -0.41
     Con
    -0.40
    Con
    -0.39
    POSITIVE LOGITS
     itſelf
    0.99
    ValueStyle
    0.92
    PyExc
    0.83
    
    0.82
    دانشنامهٔ
    0.81
    PreferredItem
    0.81
    脚注の使い方
    0.80
    enumi
    0.80
     Monfieur
    0.79
    ChildScrollView
    0.78
    Activations Density 0.058%

    No Known Activations