© 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. 1-RES-MATRYOSHKA-DC
    7. 298
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the possession or occurrence of the word "have" in various contexts

    oai_token-act-pair · gpt-4.1-nano
    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
     serem
    -0.63
     मैं
    -0.57
     Whitaker
    -0.56
     caller
    -0.56
     StatelessWidget
    -0.56
    appi
    -0.55
     sería
    -0.54
    eamiento
    -0.54
     proprement
    -0.54
     serían
    -0.53
    POSITIVE LOGITS
     have
    2.75
    have
    2.44
     Have
    2.41
     has
    2.33
    Have
    2.25
     HAVE
    2.25
     had
    2.13
    has
    2.02
    HAVE
    2.02
     Has
    1.99
    Activations Density 1.354%

    No Known Activations