© 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. 0-RES-MATRYOSHKA-DC
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "constantly" in the text

    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
     frequent
    -0.71
    frequent
    -0.68
     ujednoznacz
    -0.61
     commonly
    -0.52
     consistent
    -0.51
     frecuentes
    -0.51
     Wicidata
    -0.50
    Frequent
    -0.49
     Frequent
    -0.49
     frecuente
    -0.48
    POSITIVE LOGITS
     constantly
    2.22
     continually
    1.45
     constamment
    1.40
     constantemente
    1.32
     ständig
    1.30
     постоянно
    1.13
     continuamente
    1.06
     continuously
    1.03
     incessantly
    0.93
    不断
    0.93
    Activations Density 0.002%

    No Known Activations