© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 663
    Prev
    Next
    INDEX
    Explanations

    online gambling-related content like casino games and online slots, as well as technical language about remote control and engineering

    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
     فريبيس
    -0.91
    transQ
    -0.87
    GraphicsUnit
    -0.79
     '\\;'
    -0.79
    ImageContext
    -0.78
    THISDAY
    -0.75
    WebServlet
    -0.71
    ConstraintMaker
    -0.71
    mbggenerated
    -0.70
     MERCHANTABILITY
    -0.70
    POSITIVE LOGITS
     online
    1.10
     Online
    0.94
     cheap
    0.88
     murah
    0.80
    online
    0.78
    Online
    0.77
     Cheap
    0.76
     best
    0.74
     free
    0.71
     ONLINE
    0.70
    Activations Density 1.161%

    No Known Activations