© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16259
    Prev
    Next
    INDEX
    Explanations

    references to honorable titles or positions in a legal context

    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
     initComponents
    -0.57
    `;
    -0.56
    gevens
    -0.45
    IContainer
    -0.45
     Poc
    -0.45
    ↵↵
    -0.44
    '){
    -0.44
    ]){
    -0.44
    IComponent
    -0.44
    Przypisy
    -0.44
    POSITIVE LOGITS
     Meksiku
    1.03
     Honorable
    1.02
     '\\;'
    0.91
     Honourable
    0.87
    RectangleBorder
    0.86
    findpost
    0.85
     HONORABLE
    0.84
    Honorable
    0.84
    DockStyle
    0.82
     Ceramby
    0.81
    Activations Density 0.001%

    No Known Activations