© 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. 13866
    Prev
    Next
    INDEX
    Explanations

    instances of smiles or smiling expressions

    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
     Corintios
    -0.76
    المناصب
    -0.73
     Hoof
    -0.72
    (/^
    -0.72
     BytesLike
    -0.70
    Trama
    -0.70
    ıştı
    -0.69
    principalColumn
    -0.69
    SGS
    -0.69
    Referencies
    -0.68
    POSITIVE LOGITS
     Smile
    1.27
    Smile
    1.25
     smile
    1.22
     smiles
    1.08
    smile
    1.05
     Smiling
    1.05
     SMI
    1.03
     Smiles
    1.02
    Smiles
    0.99
     smiled
    0.94
    Activations Density 0.003%

    No Known Activations