© 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. 55
    Prev
    Next
    INDEX
    Explanations

    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
     appunto
    -0.49
     itself
    -0.44
     anyway
    -0.43
     respectively
    -0.41
     nonetheless
    -0.40
    hyrchwyd
    -0.37
     ddelweddau
    -0.36
     anlam
    -0.36
    IVEREF
    -0.36
    XmlAccessorType
    -0.35
    POSITIVE LOGITS
     للمعارف
    0.72
     مشين
    0.69
     initComponents
    0.65
    Биография
    0.64
    <bos>
    0.63
    Карьера
    0.60
     disambiguazione
    0.60
     INVENTION
    0.59
    świet
    0.59
    utches
    0.58
    Activations Density 0.021%

    No Known Activations