© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 424
    Prev
    Next
    INDEX
    Explanations

    expressions of goodness and love in various contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     initially
    -0.69
     earlier
    -0.64
     eset
    -0.63
     vedette
    -0.63
    ราย
    -0.62
     inconvénients
    -0.60
     previously
    -0.58
     unsuccessfully
    -0.58
     flatly
    -0.57
     EARL
    -0.57
    POSITIVE LOGITS
    脚注の使い方
    0.80
    ValueStyle
    0.79
     lenker
    0.78
     autorytatywna
    0.76
     AssemblyCulture
    0.76
    tvguidetime
    0.76
     humankind
    0.75
    fillType
    0.74
     humanity
    0.72
    WriteTagHelper
    0.72
    Activations Density 7.045%

    No Known Activations