© 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. 18685
    Prev
    Next
    INDEX
    Explanations

    salutation words, particularly variations of "dear."

    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
    تقاوى
    -0.76
    writeHead
    -0.76
    AppMethodBeat
    -0.75
    IComponent
    -0.74
    anyone
    -0.70
    ftagPool
    -0.69
    ViewFeatures
    -0.69
    tagHelperRunner
    -0.67
    bibliography
    -0.65
    AttributeSet
    -0.65
    POSITIVE LOGITS
     DEAR
    1.30
     Dear
    1.26
    DEAR
    1.25
     dear
    1.08
    Dear
    1.07
    dear
    0.97
     Dearborn
    0.79
    Dearest
    0.75
    Beloved
    0.75
     dearest
    0.73
    Activations Density 0.003%

    No Known Activations