© 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. 12-RES-MATRYOSHKA-DC
    7. 9769
    Prev
    Next
    INDEX
    Explanations

    references to unlawful conduct or discrimination related to gender or sexual harassment

    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
     يتيمه
    -0.60
     Lilli
    -0.58
    caman
    -0.56
     incomplète
    -0.56
     Teut
    -0.54
    ticio
    -0.52
     depositors
    -0.52
     rowspan
    -0.52
     Occ
    -0.52
     Wilk
    -0.52
    POSITIVE LOGITS
    queryInterface
    0.88
    RTLD
    0.81
     ✭✭
    0.72
    RTLR
    0.71
     AspNetCore
    0.68
    Personendaten
    0.67
    pergillus
    0.66
     ChromeDriver
    0.66
    MethodManager
    0.65
    sizeCache
    0.64
    Activations Density 0.013%

    No Known Activations