© 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. 98028
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns/articles

    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
    ьаж
    -0.78
     الدولى
    -0.75
     propOrder
    -0.74
    PYX
    -0.74
    gameserver
    -0.73
    adaptiveStyles
    -0.73
     betweenstory
    -0.72
    脚注の使い方
    -0.71
    :✨
    -0.69
    TintMode
    -0.68
    POSITIVE LOGITS
     arms
    0.59
    ReusableCell
    0.56
     Arms
    0.45
     braços
    0.44
    dataloader
    0.41
    勃
    0.38
    Arms
    0.38
     brazos
    0.36
     vaut
    0.35
     bien
    0.35
    Activations Density 0.001%

    No Known Activations