© 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. 721
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    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
     propOrder
    -0.96
    verwijspagina
    -0.81
    kháu
    -0.74
     InputDecoration
    -0.72
     ویکی‌پدیا
    -0.64
     BoxDecoration
    -0.60
     Metallurgy
    -0.58
    StoreMessageInfo
    -0.58
     turística
    -0.57
    JoinTable
    -0.57
    POSITIVE LOGITS
    theless
    0.70
    es
    0.59
     R
    0.58
    StateList
    0.55
     Z
    0.55
     memberId
    0.53
    R
    0.53
    er
    0.52
    ting
    0.52
    igl
    0.51
    Activations Density 0.072%

    No Known Activations