© 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. 3-RES-MATRYOSHKA-DC
    7. 3089
    Prev
    Next
    INDEX
    Explanations

    the word "relationship" and words around it

    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
     RELATIVE
    -0.61
     Relative
    -0.60
     popolari
    -0.60
     Containing
    -0.58
     autorytatywna
    -0.57
    datalist
    -0.57
    intar
    -0.55
    GOTREF
    -0.55
    listdir
    -0.55
    publique
    -0.54
    POSITIVE LOGITS
     relationship
    3.06
     relationships
    2.83
     Relationship
    2.77
    relationship
    2.70
    Relationship
    2.64
     RELATIONSHIP
    2.64
     Relationships
    2.63
    Relationships
    2.48
    relationships
    2.41
     RELATION
    2.31
    Activations Density 0.055%

    No Known Activations