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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1096
    Prev
    Next
    INDEX
    Explanations

    mentions of love and related virtues

    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
     daz
    -0.85
     pleaſure
    -0.75
    Datuak
    -0.70
     purpoſe
    -0.69
     ſur
    -0.68
     houſe
    -0.65
     Gaetano
    -0.65
    ؤلاء
    -0.64
     leth
    -0.63
     unſ
    -0.62
    POSITIVE LOGITS
     love
    1.94
     LOVE
    1.84
    LOVE
    1.74
     Love
    1.70
    love
    1.64
    Love
    1.59
     loves
    1.52
    loves
    1.51
     loving
    1.42
     Loves
    1.38
    Activations Density 0.185%

    No Known Activations