© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2986
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    __.__
    -0.46
    AlterField
    -0.43
    dor
    -0.43
    ++.
    -0.42
     taglia
    -0.42
    UIControlState
    -0.41
    wpi
    -0.41
    )._
    -0.41
    ector
    -0.40
     برانيه
    -0.40
    POSITIVE LOGITS
    WebElementEntity
    0.84
    хьтан
    0.80
     AssemblyCulture
    0.80
     CreateTagHelper
    0.76
     AllAfrica
    0.73
    bootstrapcdn
    0.71
     فريبيس
    0.65
     noDo
    0.65
    AndroidJUnit
    0.64
     ModelExpression
    0.64
    Activations Density 0.008%

    No Known Activations