© 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
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 29472
    Prev
    Next
    INDEX
    Explanations

    the word "smile" with varying degrees of surrounding context and related words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Avery
    -0.70
    躇
    -0.68
     Avery
    -0.67
     popolari
    -0.66
     délic
    -0.63
    naughty
    -0.62
    jsdelivr
    -0.62
     naughty
    -0.60
     PCP
    -0.60
     kurzem
    -0.60
    POSITIVE LOGITS
     smile
    1.27
    Smile
    1.20
     Smile
    1.18
     smiles
    1.17
    smile
    1.02
     smiled
    1.01
     Smiles
    0.99
    Smiles
    0.93
     smiling
    0.92
     Smiling
    0.92
    Activations Density 0.004%

    No Known Activations