© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 31976
    Prev
    Next
    INDEX
    Explanations

    expressions of well-wishing and positivity

    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
     thanks
    -0.78
    thanks
    -0.73
     THANKS
    -0.73
     thank
    -0.71
     Thanks
    -0.69
    Thanks
    -0.69
     gracias
    -0.68
     takk
    -0.67
     thankful
    -0.64
     Thx
    -0.63
    POSITIVE LOGITS
    rungsseite
    0.86
    
    0.71
    
    0.66
    Portail
    0.62
    NameInMap
    0.57
    kháu
    0.56
    HtmlAttribute
    0.56
     TestBed
    0.55
    المناصب
    0.55
    CPtr
    0.55
    Activations Density 0.025%

    No Known Activations