© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2480
    Prev
    Next
    INDEX
    Explanations

    proper nouns or brands

    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
    ური
    -0.76
    uliert
    -0.69
    Hozzáférés
    -0.69
    Identyfik
    -0.67
    Datuak
    -0.66
     recev
    -0.66
     AssemblyCulture
    -0.64
    +#+#
    -0.63
     reasonable
    -0.63
    MIDDLEWARE
    -0.62
    POSITIVE LOGITS
     ràng
    0.64
     Rask
    0.63
    TouchEvent
    0.62
    reactstrap
    0.57
    ربای
    0.56
     numberOfRows
    0.52
     EconPapers
    0.52
    RSC
    0.50
     ganglion
    0.50
     uite
    0.50
    Activations Density 1.412%

    No Known Activations