© 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. 10478
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "heart" or emotional connections

    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
    ValueStyle
    -0.91
    нодоро
    -0.74
     Réponses
    -0.73
    🏿
    -0.73
    onucleotides
    -0.69
    ExtendWith
    -0.67
     OGS
    -0.66
     AssemblyCompany
    -0.65
    standers
    -0.65
    erie
    -0.65
    POSITIVE LOGITS
     HEART
    0.96
    HEART
    0.82
     hearts
    0.78
    hearts
    0.76
     Heart
    0.76
     heart
    0.74
     Hearts
    0.73
    Hearts
    0.71
     host
    0.68
    heart
    0.68
    Activations Density 0.012%

    No Known Activations