© 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. 3-RES-MATRYOSHKA-DC
    7. 109
    Prev
    Next
    INDEX
    Explanations

    sentences that use the verb "have" or its contractions

    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
     purpoſe
    -0.97
     ſtate
    -0.91
     Chriftian
    -0.91
     houſe
    -0.86
     pleaſure
    -0.85
     leçon
    -0.85
     circulaire
    -0.85
     Jefus
    -0.84
     pauv
    -0.84
     Monfieur
    -0.84
    POSITIVE LOGITS
     have
    2.20
     has
    2.06
     had
    2.03
     Have
    1.72
    have
    1.70
     HAVE
    1.63
     Has
    1.59
    Have
    1.55
     HAS
    1.51
    has
    1.42
    Activations Density 1.378%

    No Known Activations