© 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. 2575
    Prev
    Next
    INDEX
    Explanations

    names of people and some related words such as family relations

    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
     began
    -0.84
     joined
    -0.78
     appeared
    -0.78
    began
    -0.71
     returned
    -0.69
     commenced
    -0.69
     depuis
    -0.64
     since
    -0.64
     jumped
    -0.62
     started
    -0.62
    POSITIVE LOGITS
    出版年
    0.66
     grise
    0.64
     dying
    0.64
     semper
    0.63
     Dying
    0.60
     beque
    0.60
     äls
    0.58
    parsedMessage
    0.57
     aima
    0.57
     leef
    0.54
    Activations Density 0.402%

    No Known Activations