© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16926
    Prev
    Next
    INDEX
    Explanations

    variants of the word "give"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     provided
    -0.82
     Provided
    -0.77
    providers
    -0.74
     bienvenue
    -0.73
    provided
    -0.73
     Watkins
    -0.71
    sizlik
    -0.71
     createDate
    -0.71
     Hemis
    -0.71
     provision
    -0.70
    POSITIVE LOGITS
     GIVE
    0.75
    Caesar
    0.73
    HtmlAttribute
    0.72
    Give
    0.71
    IUrlHelper
    0.71
    autoconfigure
    0.70
     MotionEvent
    0.70
    CodeAttribute
    0.69
    GIVE
    0.69
    ArgsConstructor
    0.68
    Activations Density 0.071%

    No Known Activations