© 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. 665
    Prev
    Next
    INDEX
    Explanations

    strings of characters typically found in code files and network configurations like keys, identifiers, and file paths.

    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
    i
    -0.69
    y
    -0.63
    o
    -0.60
    yta
    -0.60
    yed
    -0.59
    e
    -0.59
    iit
    -0.58
    eer
    -0.57
    rés
    -0.57
    oat
    -0.57
    POSITIVE LOGITS
     sherds
    0.92
     Потому
    0.73
     noastre
    0.73
     normaux
    0.72
     Phry
    0.72
     twain
    0.71
    DockStyle
    0.70
     Jesuits
    0.69
     preghi
    0.69
     picioare
    0.67
    Activations Density 1.992%

    No Known Activations