© 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. 5972
    Prev
    Next
    INDEX
    Explanations

    phrases and words that indicate relationships

    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
     SAMPLES
    -0.87
     Gaj
    -0.83
    Datuak
    -0.81
    Vog
    -0.79
     sanitarias
    -0.78
     AMI
    -0.74
    getCmp
    -0.74
     lẫn
    -0.73
    worpen
    -0.73
     cork
    -0.71
    POSITIVE LOGITS
     relationships
    1.66
     relationship
    1.57
    Relationships
    1.51
     Relationship
    1.46
     Relationships
    1.46
    relationships
    1.38
    Relationship
    1.34
    relationship
    1.23
     RELATIONSHIP
    1.22
     relations
    1.20
    Activations Density 0.031%

    No Known Activations