© 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. 94841
    Prev
    Next
    INDEX
    Explanations

    time related prepositions

    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
    UnknownFields
    -0.84
    󠁢
    -0.69
    ">—
    -0.69
    NameInMap
    -0.68
    ViewFeatures
    -0.68
    TintMode
    -0.67
     Réponses
    -0.67
     Italijani
    -0.65
     HFILL
    -0.64
     Bioaccumulative
    -0.64
    POSITIVE LOGITS
    ẵng
    0.44
     sejak
    0.43
     từ
    0.43
     sometime
    0.42
     recent
    0.41
    Chham
    0.40
     طی
    0.38
     conséquence
    0.38
    tachten
    0.37
    équi
    0.37
    Activations Density 0.004%

    No Known Activations