© 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. 332
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of computer hardware or software

    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
    :✨
    -0.51
     FTIR
    -0.49
    zieć
    -0.49
    findpost
    -0.49
     IFTTT
    -0.49
     onOptions
    -0.48
    TintMode
    -0.47
     disarm
    -0.47
     Receptor
    -0.47
    Skocz
    -0.46
    POSITIVE LOGITS
     memory
    1.56
     Memory
    1.33
    memory
    1.30
    Memory
    1.21
     MEMORY
    1.17
     storage
    1.16
     mémoire
    1.08
     memoria
    1.05
    MEMORY
    1.02
     Storage
    0.99
    Activations Density 3.074%

    No Known Activations