© 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. 400
    Prev
    Next
    INDEX
    Explanations

    news articles, with an emphasis on numbers, locations, people speaking, government, and legal issues.

    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
    Whilst
    -1.11
     Whilst
    -1.11
     ایشان
    -0.91
     whilst
    -0.90
     אשר
    -0.84
     skall
    -0.83
    mıştır
    -0.82
     می‌باشد
    -0.82
    に於
    -0.81
    非常的
    -0.79
    POSITIVE LOGITS
     Wednesday
    1.12
     Thursday
    1.11
     Tuesday
    1.11
     amid
    1.00
     lawmakers
    0.99
    Wednesday
    0.97
     Friday
    0.95
    Thursday
    0.94
     Monday
    0.94
    Tuesday
    0.93
    Activations Density 3.097%

    No Known Activations