© 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. 5-CLT-HP
    7. 857
    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
     المعيارى
    -0.71
    TagMode
    -0.71
    tagHelperRunner
    -0.68
    WriteTagHelper
    -0.63
    ValueStyle
    -0.60
     Betracht
    -0.58
     '\\;'
    -0.57
    minecraftforge
    -0.56
    kloped
    -0.56
    perate
    -0.56
    POSITIVE LOGITS
    Referències
    0.61
    そうそう
    0.53
     champs
    0.52
     Walkover
    0.50
     imaginable
    0.50
     drafts
    0.48
     Champs
    0.47
    ην
    0.46
    almost
    0.45
    舊
    0.45
    Activations Density 0.007%

    No Known Activations