© 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. 4-CLT-HP
    7. 719
    Prev
    Next
    INDEX
    Explanations

    prepositions and locations

    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
    帖最后由
    -0.88
    Билгалдахарш
    -0.82
    脚注の使い方
    -0.81
     مشين
    -0.75
    GEBURTSDATUM
    -0.73
     мәкал
    -0.72
     للمعارف
    -0.69
    fromnode
    -0.66
     propOrder
    -0.65
    AnchorStyles
    -0.62
    POSITIVE LOGITS
    èmes
    0.46
    aurait
    0.42
    LLocation
    0.42
     række
    0.41
     concentration
    0.41
    edith
    0.39
    lichter
    0.39
    side
    0.38
    Читать
    0.38
     numériques
    0.38
    Activations Density 0.004%

    No Known Activations