© 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. 22-RES-MATRYOSHKA-DC
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    locations or organizations, especially in Malaysia, and words associated with political figures

    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.22.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.22.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
    HostException
    -0.72
     getItemId
    -0.69
    帖最后由
    -0.67
     Normdatei
    -0.66
    RegressionTest
    -0.62
     AppColors
    -0.62
    berdayakan
    -0.61
     rajut
    -0.59
     BYU
    -0.59
     vapors
    -0.59
    POSITIVE LOGITS
     Malaysia
    1.19
     Malaysian
    1.15
     Singapore
    1.06
    Malaysia
    1.06
     Malay
    1.06
    Malay
    1.00
     Kuala
    0.97
    Singapore
    0.94
     Penang
    0.91
     Johor
    0.89
    Activations Density 1.406%

    No Known Activations