© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41331
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     hundred
    -0.91
    hundred
    -0.89
     shed
    -0.88
     dozen
    -0.84
     let
    -0.79
    __":
    -0.75
    dozen
    -0.73
     centaines
    -0.70
    shed
    -0.69
     HUND
    -0.69
    POSITIVE LOGITS
    enterOuterAlt
    0.80
    WebElementEntity
    0.71
    webElementXpaths
    0.64
    AddHtmlAttribute
    0.62
    AddTagHelper
    0.61
     oysters
    0.60
     Exactos
    0.60
    Personendaten
    0.60
    adaptiveStyles
    0.59
    IVEREF
    0.59
    Activations Density 0.477%

    No Known Activations