Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1634
    Prev
    Next
    INDEX
    Explanations

    verbs related to obtaining or achieving something, often in business and finance

    oai_token-act-pair · gemini-2.0-flash

    get/getting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    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
     незавершена
    -0.69
     referenties
    -0.59
    ,:);
    -0.56
    CloseOperation
    -0.56
    utate
    -0.55
    httphttps
    -0.53
    ศาสตร์
    -0.53
    ✭
    -0.52
    PDOException
    -0.52
     autorytatywna
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.57
    Personensuche
    0.56
     cabecera
    0.51
     gyrus
    0.48
     pengend
    0.48
     výro
    0.45
     samfun
    0.44
     tå
    0.44
     blocco
    0.44
     rayures
    0.44
    Activations Density 5.024%

    No Known Activations