© 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. 904
    Prev
    Next
    INDEX
    Explanations

    numbers or number ranges within text

    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
    \{\\
    -0.89
    новниш
    -0.76
    tableFuture
    -0.74
    rizona
    -0.74
     nonatomic
    -0.68
     Мексичка
    -0.68
    NUMX
    -0.68
    IUrlHelper
    -0.68
    WebVitals
    -0.68
    ParallelGroup
    -0.63
    POSITIVE LOGITS
    –
    1.28
     až
    1.12
    ～
    1.00
     hingga
    0.97
     through
    0.95
     sampai
    0.95
     تا
    0.92
    ~
    0.91
    〜
    0.91
     to
    0.88
    Activations Density 1.652%

    No Known Activations