© 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. 5-CLT-HP
    7. 98133
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.73
    AddHtmlAttribute
    -0.68
    abetes
    -0.67
     snippetHide
    -0.65
     ciudadana
    -0.65
    ILAR
    -0.64
    DllImport
    -0.62
    awaiter
    -0.60
    extAlignment
    -0.60
    دانشنامهٔ
    -0.59
    POSITIVE LOGITS
    mybatisplus
    0.52
     kasarigan
    0.43
    lapsingToolbar
    0.42
    Eksterne
    0.42
     censiti
    0.39
    bre
    0.39
     emploi
    0.38
    use
    0.37
    ondo
    0.37
    Ons
    0.37
    Activations Density 0.003%

    No Known Activations